Effective Altruism Forum
EA Forum

Hide table of contents
by johnnylin
4 min read 2

9

AI safetyAnnouncements and updatesResearch
Frontpage
This is a linkpost for https://neuronpedia.org

EA CONTEXT

Neuronpedia is funded by a short-term grant from an EA fund which ends in a few weeks. In lieu of the traditional "final report/paper" they requested, I am posting my project on the EA forum, so that you can play the game, provide feedback, and hopefully contribute.

I am new this forum, so I apologize if this is not the right format/place for this. 

 

WHAT'S NEURONPEDIA?

Neuronpedia is an AI safety game that documents and explains neurons (and features found with Sparse Autoencoders) in modern AI models. It aims to be the Wikipedia for interpreting AI models, where the contributions come from users playing a game. Neuronpedia also wants to connect the general public to AI safety, so it's designed to not require any technical knowledge to play. 

 

OBJECTIVES

  1. Crowdsource AI interpretability to help build safer AI ("Geoguessr for AI")
  2. Increase public engagement, awareness, and education in AI safety

 

LONG TERM VISION

Anyone can upload their LLM, and then Neuronpedia does all the interpretability work: generate activation texts, make features/directions, generate explanations, collect human/player explanations, scoring explanations, and produce/export all the data via an API or to files. Basically, a one stop shop for interpretability.

  • Neuronpedia is not that far off from this, feature-wise. We have done every part of those tasks, but haven't built the tooling to do them all in one streamlined process.

 

STATUS

  • Neuronpedia's v1.0 is ready for public release and will be posted in more places in the coming days.
  • During the beta period, we collected 3,000+ explanations from players, over half of which beat GPT-4's explanations, when scored using OpenAI's Automated Interpretability. Over 500 votes have been collected, and over 2,000 explanations have been verified.
  • Initially only explaining neurons, Neuronpedia now also has features/directions found with Sparse Autoencoders, thanks to researchers Hoagy Cunningham, Logan Riggs, and Aiden Ewart.

 

WHAT YOU CAN DO

  1. Play @ neuronpedia.org - you can log in with email, Apple, Google, or GitHub.
  2. Tell a friend - even those who are not interested in AI.
  3. Give feedback, ideas, and ask questions.
  4. Join Discord - https://discord.gg/kpEJWgvdAx 

 

FEATURES

  • Pixel-based role-playing game complete with graphics/animations, leveling up, equipment, potions, etc.
  • Explain Mode - View activations for a neuron/feature and explain them.
  • Dig Mode - Verify the accuracy of explanations.
  • In-game Shop - Earning "Bones" (in-game currency) by playing Dig Mode lets you buy stuff like colorful hats for you and your character's pet, etc.
  • Leaderboard - Compete against other players.
  • Mobile Optimized - Play on the bus or when you're having trouble falling asleep from AI nightmares.
  • Sharing / Summary
  • View Data - Anyone can browse the current results, vote, and even comment on neurons/features: http://neuronpedia.org/gpt2-small 
  • Test New Activations - You can test new activation texts for every neuron/feature.

 

MOST SIGNIFICANT FLAWS

  • Scoring - OpenAI's Automated Interpretability is good, but it often doesn't take context of tokens into account. For example, if the highest scoring token of the top 20 activations are the word "cat" in the fragments "blue cat", "white cat", "black cat", the highest scoring explanation should be "cat with a color before it" - but often times the explanation "the word 'cat'" will have a higher score.
    • Solution 1: Train a model specific to scoring that also look at scoring. This is a work in progress - we have enough activations/explanations that we can do this.
    • Solution 2: User scoring. This is implemented via "Dig Mode" in the game, but I haven't had time to connect it to the "Explain Mode" to complete the loop of generating a score. Also, it's asynchronous, so it doesn't immediately give the user feedback.
    • Solution 3: Regex or other non-AI based scoring. This was suggested by player duck-master, but I haven't had time to figure out the details or implement it.
  • Polysemanticity - I'm grateful for the features/directions from Hoagy/Logan/Aiden - they are less polysemantic than neurons - but they're limited in number (~3000 non-dead features, ~800 of those are somewhat low activating) due to our lack of GPU resources and their lack of time. I believe that more compute can result in even better features.
  • Onboarding is lacking / rough - there should be a much more graceful transition in difficulty for the game from onboarding to the real game - e.g, give users some fake puzzles first so they can get the hang of it.
    • Solution: Fairly straightforward to do this but haven't had time.
  • Optimizing for Fun vs Usefulness - Building a game around what AI safety researchers need has been a tough but interesting challenge. In a pure game, your only objective is to get the player glued to the screen, and you can adjust whatever you like to make this happen - for example, you could generate thousands of really easy puzzles (e.g, angry birds, clicker games) that make the player feel good. Word games like Wordle have a definite solution, making "winning" more satisfying/fair. For Neuronpedia, the difficulty is that there is not a "right answer", or you won't get the best answer, or the scoring/results will seem unfair.
    • Solution - There's a lot to say here, but I'm optimistic and have seen that tweaking gameplay using a bit of creativity/cleverness can overcome these problems. Also - there are some very involved players who are happy to contribute to AI safety even if the game isn't as engaging as Zelda or Mario.

 

WHAT'S NEXT FOR NEURONPEDIA

  • Features (other than the ones mentioned in "flaws" sections above)
    • Data / ML
      • Let anyone upload their own LLMs
      • Let anyone upload their own features/directions
      • More and Better Models, Layers, Directions/Features
    • Game
      • New Game Types/Modes - PvP, teams, contests, etc
        • Turn other Interp needs into new game modes
      • Weekly Summary and other notifications
      • Character / Profile Refresh
      • Challenges / Contests
      • Achievements
      • Unlockables (robes, shoes, gloves, wands, etc)
    • General
      • Code cleanup/backend optimizations/fixes
  • Funding - Neuronpedia's three-month EA grant runs out soon. I've spent personal funds on keeping the site up, servers/inference machines, and other bills. I'd really like to keep working on it full time, so let me know (johnny@neuronpedia.org) if you're interested in supporting it - or if you can recommend me for a grant. I'm also open to investment for equity, but I'm not sure if an AI safety game will beat the S&P 500 - though you could potentially profit from reducing humanity's AI risk!

9

0
0

Reactions

0
0

More posts like this

Comments2


Sorted by
New & upvoted
Click to highlight new comments since:
XaviCF2
0
0

Having just spent the last 30 minutes trying it out, it's safe to say that I'm very excited about Neuronpedia. It's a fun, collaborative, positive-sum game with an excellent user experience, making it easy and enjoyable to play.

This is a great idea with great execution - I'd recommend giving it a go if you're currently on the fence. Congratulations on public release!

Reply
johnnylin1
0
0

Awesome - thanks Xavi. I just saw that you joined the Discord as well. Welcome!

Reply
Curated and popular this week
LintzA
 ·  · 15m read
 · 
Cross-posted to Lesswrong Introduction Several developments over the past few months should cause you to re-evaluate what you are doing. These include: 1. Updates toward short timelines 2. The Trump presidency 3. The o1 (inference-time compute scaling) paradigm 4. Deepseek 5. Stargate/AI datacenter spending 6. Increased internal deployment 7. Absence of AI x-risk/safety considerations in mainstream AI discourse Taken together, these are enough to render many existing AI governance strategies obsolete (and probably some technical safety strategies too). There's a good chance we're entering crunch time and that should absolutely affect your theory of change and what you plan to work on. In this piece I try to give a quick summary of these developments and think through the broader implications these have for AI safety. At the end of the piece I give some quick initial thoughts on how these developments affect what safety-concerned folks should be prioritizing. These are early days and I expect many of my takes will shift, look forward to discussing in the comments!  Implications of recent developments Updates toward short timelines There’s general agreement that timelines are likely to be far shorter than most expected. Both Sam Altman and Dario Amodei have recently said they expect AGI within the next 3 years. Anecdotally, nearly everyone I know or have heard of who was expecting longer timelines has updated significantly toward short timelines (<5 years). E.g. Ajeya’s median estimate is that 99% of fully-remote jobs will be automatable in roughly 6-8 years, 5+ years earlier than her 2023 estimate. On a quick look, prediction markets seem to have shifted to short timelines (e.g. Metaculus[1] & Manifold appear to have roughly 2030 median timelines to AGI, though haven’t moved dramatically in recent months). We’ve consistently seen performance on benchmarks far exceed what most predicted. Most recently, Epoch was surprised to see OpenAI’s o3 model achi
Dr Kassim
 ·  · 4m read
 · 
Hey everyone, I’ve been going through the EA Introductory Program, and I have to admit some of these ideas make sense, but others leave me with more questions than answers. I’m trying to wrap my head around certain core EA principles, and the more I think about them, the more I wonder: Am I misunderstanding, or are there blind spots in EA’s approach? I’d really love to hear what others think. Maybe you can help me clarify some of my doubts. Or maybe you share the same reservations? Let’s talk. Cause Prioritization. Does It Ignore Political and Social Reality? EA focuses on doing the most good per dollar, which makes sense in theory. But does it hold up when you apply it to real world contexts especially in countries like Uganda? Take malaria prevention. It’s a top EA cause because it’s highly cost effective $5,000 can save a life through bed nets (GiveWell, 2023). But what happens when government corruption or instability disrupts these programs? The Global Fund scandal in Uganda saw $1.6 million in malaria aid mismanaged (Global Fund Audit Report, 2016). If money isn’t reaching the people it’s meant to help, is it really the best use of resources? And what about leadership changes? Policies shift unpredictably here. A national animal welfare initiative I supported lost momentum when political priorities changed. How does EA factor in these uncertainties when prioritizing causes? It feels like EA assumes a stable world where money always achieves the intended impact. But what if that’s not the world we live in? Long termism. A Luxury When the Present Is in Crisis? I get why long termists argue that future people matter. But should we really prioritize them over people suffering today? Long termism tells us that existential risks like AI could wipe out trillions of future lives. But in Uganda, we’re losing lives now—1,500+ die from rabies annually (WHO, 2021), and 41% of children suffer from stunting due to malnutrition (UNICEF, 2022). These are preventable d
Rory Fenton
 ·  · 6m read
 · 
Cross-posted from my blog. Contrary to my carefully crafted brand as a weak nerd, I go to a local CrossFit gym a few times a week. Every year, the gym raises funds for a scholarship for teens from lower-income families to attend their summer camp program. I don’t know how many Crossfit-interested low-income teens there are in my small town, but I’ll guess there are perhaps 2 of them who would benefit from the scholarship. After all, CrossFit is pretty niche, and the town is small. Helping youngsters get swole in the Pacific Northwest is not exactly as cost-effective as preventing malaria in Malawi. But I notice I feel drawn to supporting the scholarship anyway. Every time it pops in my head I think, “My money could fully solve this problem”. The camp only costs a few hundred dollars per kid and if there are just 2 kids who need support, I could give $500 and there would no longer be teenagers in my town who want to go to a CrossFit summer camp but can’t. Thanks to me, the hero, this problem would be entirely solved. 100%. That is not how most nonprofit work feels to me. You are only ever making small dents in important problems I want to work on big problems. Global poverty. Malaria. Everyone not suddenly dying. But if I’m honest, what I really want is to solve those problems. Me, personally, solve them. This is a continued source of frustration and sadness because I absolutely cannot solve those problems. Consider what else my $500 CrossFit scholarship might do: * I want to save lives, and USAID suddenly stops giving $7 billion a year to PEPFAR. So I give $500 to the Rapid Response Fund. My donation solves 0.000001% of the problem and I feel like I have failed. * I want to solve climate change, and getting to net zero will require stopping or removing emissions of 1,500 billion tons of carbon dioxide. I give $500 to a policy nonprofit that reduces emissions, in expectation, by 50 tons. My donation solves 0.000000003% of the problem and I feel like I have f
Recent opportunities in AI safety
3
Apply to become a Futurekind AI Facilitator or Mentor (deadline: April 10)
Jay Luong
· · 2m read
0
0
30
Apply to MATS 8.0!
Ryan Kidd
·
0
0
35
AIS Netherlands is looking for a Founding Executive Director (EOI form)
7 authors
· · 5m read
4
4
View more