timaeus-research / devinterp
Tools for studying developmental interpretability in neural networks.
☆86Updated last month
Alternatives and similar repositories for devinterp:
Users that are interested in devinterp are comparing it to the libraries listed below
- Mechanistic Interpretability Visualizations using React☆233Updated 3 months ago
- ☆210Updated 5 months ago
- ☆121Updated last year
- (Model-written) LLM evals library☆18Updated 3 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆206Updated last year
- ☆61Updated 4 months ago
- ☆26Updated 11 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆189Updated 3 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆116Updated 2 years ago
- 🧠 Starter templates for doing interpretability research☆67Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆161Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆226Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- Machine Learning for Alignment Bootcamp☆72Updated 2 years ago
- Sparse Autoencoder Training Library☆43Updated 4 months ago
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- ☆113Updated 7 months ago
- ☆29Updated 10 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated 11 months ago
- ☆149Updated 2 weeks ago
- we got you bro☆35Updated 7 months ago
- ☆10Updated 8 months ago
- ☆255Updated last month
- Interpreting how transformers simulate agents performing RL tasks☆78Updated last year
- ☆62Updated 2 years ago
- ☆61Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated 3 weeks ago
- Machine Learning for Alignment Bootcamp (MLAB).☆25Updated 3 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆177Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆224Updated last year