johnny

i still sometimes code things by hand

Researchers can use the Neuronpedia interactive interface here: neuronpedia.org/gemma-2-2b/gra… And we’ve provided an annotated walkthrough: github.com/safety-researc… This project was led by participants in our Anthropic Fellows program, in collaboration with Decode Research.

Announcement: we're open sourcing Neuronpedia! 🚀 This includes all our mech interp tools: the interpretability API, steering, UI, inference, autointerp, search, plus 4 TB of data - cited by 35+ research papers and used by 50+ write-ups. What you can do with OSS Neuronpedia: 🧵

Neuronpedia now hosts Chain-of-Thought! Steer and inspect Deepseek-R1-Distill-Llama-8B with SAEs trained by @Open_MOSS on @neuronpedia (linked below). One fun initial result: the model can easily be steered into "overthinking/anxious" mode with a single latent.

Google DeepMind has a new way to look inside an AI’s “mind” trib.al/UN5W3Uh

Gemma Scope allows us to study how features evolve throughout the model and interact to create more complex ones. Want to learn more? Here’s an interactive demo made by @neuronpedia - no coding necessary ↓ dpmd.ai/gemma-scope

Want to learn more? @neuronpedia have made a gorgeous interactive demo walking you through what Sparse Autoencoders are, and what Gemma Scope can do. If this could happen pre-launch, I'm excited to see what the community will do with Gemma Scope now! neuronpedia.org/gemma-scope

Sparse Autoencoders act like a microscope for AI internals. They're a powerful tool for interpretability, but training costs limit research Announcing Gemma Scope: An open suite of SAEs on every layer & sublayer of Gemma 2 2B & 9B! We hope to enable even more ambitious work

exciting new research from @apolloaisafety and @jordantensor: E2E SAEs (w/ ~700k features) are now live on @neuronpedia - the first to use dual UMAPs for visual comparison and exploration between SAE training methods. check it out at neuronpedia.org/gpt2sm-apollojt

Terrific work by @saprmarks and team! 🥳 We really enjoyed working with them to get their Sparse Autoencoders onto @neuronpedia. You can explore, search, and test their 622,594 features here: neuronpedia.org/p70d-sm

6/ Oh and of course, @neuronpedia is publicly available for anyone to experiment and play with at neuronpedia.org. Let us know what you think!

5/ Thanks to @JBloomAus for support, @NeelNanda5 for TransformerLens, @ch402 @nickcammarata for inspiration from OpenAI Microscope, and William Saunders for Neuron Viewer. It's time to accelerate (interpretability research). 🚀🔬 lesswrong.com/posts/BaEQoxHh…

1/ Introducing Neuronpedia: an open platform for interpretability research with hosting, visualizations, and tooling for Sparse Autoencoders (SAEs). Let's try it out! ➡️ Neuronpedia lets us instantly test activations of SAE features with custom text. Here's a Star Wars feature:

Super impressed by @johnnylin's Interactive Interface for exploring my GPT2 Small SAE Features. neuronpedia.org/gpt2-small/res…. First 5000 for each layer are there with the rest coming shortly! We've updated the feature-activation highlighting to better show multiple fires per context!

best IoT feature: devices that automatically update for daylight savings time

Openly Operated wants to make privacy policies actually mean something theverge.com/2019/6/18/1868…

twitter encourages logical local optima