callummcdougall / sae_visLinks
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆200Updated 5 months ago
Alternatives and similar repositories for sae_vis
Users that are interested in sae_vis are comparing it to the libraries listed below
Sorting:
- 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
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- ☆121Updated last year
- ☆302Updated last week
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago
- Sparsify transformers with SAEs and transcoders☆547Updated this week
- ☆96Updated last month
- ☆222Updated 7 months ago
- ☆120Updated 6 months ago
- ☆170Updated last month
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆574Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- Training Sparse Autoencoders on Language Models☆789Updated this week
- ☆42Updated 6 months ago
- ☆27Updated last year
- ☆480Updated 10 months ago
- ☆39Updated 3 weeks ago
- ☆116Updated 9 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Sparse Autoencoder Training Library☆50Updated 3 weeks ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- ☆130Updated 2 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆246Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆74Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆184Updated 6 months ago
- ☆96Updated 3 months ago