EleutherAI / sparsifyLinks
Sparsify transformers with SAEs and transcoders
☆640Updated 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☆1,001Updated this week
- ☆354Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆222Updated 10 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆683Updated last week
- Sparse Autoencoder for Mechanistic Interpretability☆276Updated last year
- ☆530Updated last year
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- ☆247Updated last year
- ☆131Updated this week
- ☆179Updated 11 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆532Updated 2 months ago
- ☆128Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆819Updated last week
- ☆54Updated 11 months ago
- ☆190Updated last week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆315Updated 3 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆290Updated 4 months ago
- This repository collects all relevant resources about interpretability in LLMs☆375Updated 11 months ago
- ☆202Updated 11 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆207Updated 11 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆157Updated this week
- ☆126Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆229Updated 2 months ago
- ☆279Updated last year
- ☆81Updated 7 months ago
- Open source interpretability artefacts for R1.☆163Updated 6 months ago