HoagyC / sparse_codingLinks
Using sparse coding to find distributed representations used by neural networks.
☆247Updated last year
Alternatives and similar repositories for sparse_coding
Users that are interested in sparse_coding are comparing it to the libraries listed below
Sorting:
- ☆222Updated 8 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago
- ☆302Updated 2 weeks 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 …☆180Updated this week
- ☆170Updated last month
- ☆120Updated 6 months ago
- ☆96Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- ☆116Updated 9 months ago
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- Sparsify transformers with SAEs and transcoders☆547Updated this week
- ☆480Updated 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆45Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆209Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆115Updated this week
- Training Sparse Autoencoders on Language Models☆789Updated this week
- ☆42Updated 6 months ago
- Sparse probing paper full code.☆56Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- ☆156Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆93Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆167Updated last month
- ☆33Updated last week
- ☆83Updated 9 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆33Updated last year