HoagyC / sparse_codingLinks
Using sparse coding to find distributed representations used by neural networks.
☆261Updated 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:
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- ☆154Updated 8 months ago
- ☆320Updated 2 weeks ago
- ☆233Updated 10 months ago
- ☆107Updated 2 weeks ago
- ☆183Updated 2 weeks ago
- ☆503Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- ☆123Updated last year
- Sparse probing paper full code.☆58Updated last year
- ☆220Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆50Updated 8 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆48Updated last year
- ☆177Updated 8 months ago
- ☆121Updated 11 months ago
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- This repository collects all relevant resources about interpretability in LLMs☆366Updated 9 months ago
- Sparsify transformers with SAEs and transcoders☆595Updated this week
- A resource repository for representation engineering in large language models☆129Updated 8 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Training Sparse Autoencoders on Language Models☆895Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆619Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- General-purpose activation steering library☆85Updated 2 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆246Updated last month