callummcdougall / sae_visLinks
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆222Updated 10 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:
- Mechanistic Interpretability Visualizations using React☆293Updated 10 months ago
- ☆128Updated 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
- Sparse Autoencoder for Mechanistic Interpretability☆276Updated last year
- ☆354Updated 2 months ago
- Sparsify transformers with SAEs and transcoders☆644Updated this week
- ☆131Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- ☆191Updated last week
- ☆179Updated 11 months ago
- ☆29Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆54Updated 11 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆685Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- ☆74Updated 2 weeks ago
- ☆126Updated last year
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆36Updated last year
- ☆142Updated last month
- Training Sparse Autoencoders on Language Models☆1,001Updated this week
- A toolkit for describing model features and intervening on those features to steer behavior.☆207Updated 11 months ago
- ☆530Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- ☆279Updated last year
- Decoder only transformer, built from scratch with PyTorch☆31Updated 2 years ago