blei-lab / circuitryLinks
☆14Updated 10 months ago
Alternatives and similar repositories for circuitry
Users that are interested in circuitry are comparing it to the libraries listed below
Sorting:
- ☆126Updated last year
- ☆238Updated 11 months ago
- ☆68Updated 2 years ago
- ☆53Updated 9 months ago
- ☆116Updated last month
- Attribution-based Parameter Decomposition☆29Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- ☆81Updated 6 months ago
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆122Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 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 …☆207Updated last week
- ☆104Updated 6 months ago
- ☆184Updated last month
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆160Updated 2 months ago
- ☆21Updated 4 months ago
- ☆185Updated last year
- ☆335Updated last week
- Using sparse coding to find distributed representations used by neural networks.☆264Updated last year
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- nanoGPT-like codebase for LLM training☆102Updated 3 months ago
- ☆238Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- ☆53Updated last year
- ☆163Updated 9 months ago
- ☆23Updated 7 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆127Updated 8 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year