callummcdougall / sae_visLinks
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆207Updated 7 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:
- ☆123Updated last year
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- 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
- ☆320Updated 2 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- ☆233Updated 10 months ago
- Sparsify transformers with SAEs and transcoders☆595Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- ☆107Updated 2 weeks ago
- ☆28Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆183Updated 2 weeks ago
- ☆50Updated 8 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆619Updated this week
- ☆154Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 8 months ago
- ☆134Updated 4 months ago
- ☆121Updated 11 months ago
- Erasing concepts from neural representations with provable guarantees☆231Updated 6 months ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Attribution-based Parameter Decomposition☆28Updated last month
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- ☆503Updated last year
- ☆274Updated last year
- Modified to support crosscoder training.☆22Updated this week
- Training Sparse Autoencoders on Language Models☆895Updated this week