callummcdougall / sae_visLinks
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆221Updated 9 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☆289Updated 9 months ago
- ☆127Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆213Updated last week
- ☆242Updated last year
- ☆347Updated last month
- Sparse Autoencoder for Mechanistic Interpretability☆268Updated last year
- Sparsify transformers with SAEs and transcoders☆630Updated this week
- ☆187Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- ☆125Updated 2 weeks ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆674Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆270Updated last year
- ☆29Updated last year
- ☆173Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- ☆54Updated 10 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆203Updated 10 months ago
- ☆142Updated 3 weeks ago
- ☆71Updated last month
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆123Updated last year
- ☆276Updated last year
- ☆521Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆530Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Training Sparse Autoencoders on Language Models☆977Updated this week
- ☆34Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago