jbloomAus / SAEDashboardLinks
☆71Updated last month
Alternatives and similar repositories for SAEDashboard
Users that are interested in SAEDashboard are comparing it to the libraries listed below
Sorting:
- 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 …☆213Updated last week
- ☆125Updated 2 weeks ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆54Updated 10 months ago
- ☆127Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- ☆173Updated 10 months ago
- ☆242Updated last year
- ☆186Updated 2 months ago
- ☆106Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- ☆142Updated 3 weeks ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- ☆123Updated last year
- ☆34Updated last year
- ☆45Updated 8 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability