ArthurConmy / Automatic-Circuit-Discovery
☆211Updated 5 months ago
Alternatives and similar repositories for Automatic-Circuit-Discovery:
Users that are interested in Automatic-Circuit-Discovery are comparing it to the libraries listed below
- Mechanistic Interpretability Visualizations using React☆235Updated 3 months ago
- Using sparse coding to find distributed representations used by neural networks.☆224Updated last year
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- ☆113Updated 7 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆233Updated 8 months ago
- ☆121Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆163Updated this week
- ☆71Updated this week
- ☆150Updated 2 weeks ago
- ☆61Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆189Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆131Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 9 months ago
- ☆89Updated last month
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- ☆258Updated last month
- Sparse probing paper full code.☆55Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆522Updated this week
- ☆195Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- ☆23Updated 3 weeks ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆206Updated last year
- ☆131Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆494Updated this week
- Algebraic value editing in pretrained language models☆63Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆46Updated 4 months ago
- ☆80Updated 7 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆480Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆669Updated this week
- ☆32Updated 4 months ago