blei-lab / circuitryLinks
☆14Updated 11 months ago
Alternatives and similar repositories for circuitry
Users that are interested in circuitry are comparing it to the libraries listed below
Sorting:
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- ☆81Updated 7 months ago
- ☆242Updated last year
- ☆127Updated last year
- ☆54Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆216Updated this week
- nanoGPT-like codebase for LLM training☆108Updated 4 months ago
- ☆106Updated 8 months ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ☆22Updated 5 months ago
- ☆69Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Mechanistic Interpretability Visualizations using React☆291Updated 9 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆165Updated 3 months ago
- ☆189Updated 2 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆42Updated last year
- ☆127Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- ☆348Updated last month
- Modified to support crosscoder training.☆23Updated 2 months ago
- ☆53Updated last year
- ☆186Updated last year
- 🧠 Starter templates for doing interpretability research☆75Updated 2 years ago
- ☆175Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆274Updated last year
- ☆126Updated last year
- ☆71Updated last month