decoderesearch / SAELensLinks
Training Sparse Autoencoders on Language Models
☆1,104Updated 2 weeks ago
Alternatives and similar repositories for SAELens
Users that are interested in SAELens are comparing it to the libraries listed below
Sorting:
- Sparsify transformers with SAEs and transcoders☆672Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆727Updated this week
- ☆552Updated last year
- ☆366Updated 3 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆838Updated 2 months ago
- Using sparse coding to find distributed representations used by neural networks.☆289Updated 2 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆285Updated last year
- Mechanistic Interpretability Visualizations using React☆302Updated 11 months ago
- A library for mechanistic interpretability of GPT-style language models☆2,865Updated last week
- ☆259Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated 11 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆551Updated 4 months ago
- ☆191Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆919Updated last year
- ☆835Updated last month
- This repository collects all relevant resources about interpretability in LLMs☆387Updated last year
- ☆136Updated 3 weeks ago
- ☆223Updated last year
- ☆195Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆311Updated 6 months ago
- Steering Llama 2 with Contrastive Activation Addition☆196Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆231Updated last week
- Locating and editing factual associations in GPT (NeurIPS 2022)☆705Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆233Updated 4 months ago
- ☆132Updated 2 years ago
- ☆240Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆168Updated this week
- open source interpretability platform 🧠☆532Updated this week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆325Updated 4 months ago
- ☆283Updated last year