timaeus-research / devinterpLinks
Tools for studying developmental interpretability in neural networks.
☆109Updated 3 months ago
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☆293Updated 10 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆229Updated 2 months ago
- ☆247Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆128Updated last year
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- we got you bro☆36Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Erasing concepts from neural representations with provable guarantees☆238Updated 8 months ago
- (Model-written) LLM evals library☆18Updated 10 months ago
- ☆36Updated last year
- ☆29Updated last year
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆104Updated this week
- Machine Learning for Alignment Bootcamp☆79Updated 3 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆276Updated last year
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ☆65Updated 2 years ago
- METR Task Standard☆163Updated 8 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- Mechanistic Interpretability for Transformer Models☆53Updated 3 years ago
- ☆354Updated 2 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆198Updated 3 years ago
- ☆19Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆683Updated last week
- ☆81Updated 7 months ago
- Inference API for many LLMs and other useful tools for empirical research☆77Updated last week