EleutherAI / sparsifyLinks
Sparsify transformers with SAEs and transcoders
☆629Updated last week
Alternatives and similar repositories for sparsify
Users that are interested in sparsify are comparing it to the libraries listed below
Sorting:
- Training Sparse Autoencoders on Language Models☆977Updated this week
- ☆347Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆672Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆268Updated last year
- ☆521Updated last year
- Mechanistic Interpretability Visualizations using React☆289Updated 9 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
- ☆242Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆527Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆270Updated last year
- ☆125Updated 2 weeks ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆813Updated last month
- ☆173Updated 10 months ago
- ☆127Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆308Updated 2 months ago
- ☆186Updated 2 months ago
- This repository collects all relevant resources about interpretability in LLMs☆373Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆275Updated 3 months ago
- ☆54Updated 10 months ago
- ☆199Updated 10 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆203Updated 10 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆227Updated last month
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆154Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- ☆276Updated last year
- Open source interpretability artefacts for R1.☆160Updated 5 months ago
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Open-source framework for the research and development of foundation models.☆462Updated this week
- ☆230Updated last year