timaeus-research / devinterpLinks
Tools for studying developmental interpretability in neural networks.
☆100Updated last month
Alternatives and similar repositories for devinterp
Users that are interested in devinterp are comparing it to the libraries listed below
Sorting:
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- ☆233Updated 10 months ago
- ☆123Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆219Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- we got you bro☆35Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- (Model-written) LLM evals library☆18Updated 7 months ago
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆184Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- METR Task Standard☆154Updated 5 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Attribution-based Parameter Decomposition☆28Updated last month
- ☆28Updated last year
- Machine Learning for Alignment Bootcamp☆75Updated 3 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- ☆32Updated last year
- ☆99Updated 4 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated last week
- ☆63Updated 2 years ago
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- A python sdk for LLM finetuning and inference on runpod infrastructure☆12Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- Erasing concepts from neural representations with provable guarantees☆231Updated 6 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆619Updated this week
- ☆320Updated 2 weeks ago
- Inference API for many LLMs and other useful tools for empirical research☆60Updated last week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆79Updated this week