callummcdougall / sae_vis
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆189Updated 3 months ago
Alternatives and similar repositories for sae_vis:
Users that are interested in sae_vis are comparing it to the libraries listed below
- Mechanistic Interpretability Visualizations using React☆233Updated 3 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆161Updated this week
- ☆121Updated last year
- ☆255Updated last month
- Sparsify transformers with SAEs and transcoders☆494Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆224Updated last year
- ☆211Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆233Updated 8 months ago
- ☆61Updated 4 months ago
- Training Sparse Autoencoders on Language Models☆669Updated this week
- ☆149Updated 2 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- ☆71Updated this week
- ☆113Updated 7 months ago
- ☆26Updated 11 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆518Updated this week
- ☆89Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆45Updated 4 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆162Updated 4 months ago
- Erasing concepts from neural representations with provable guarantees☆226Updated last month
- ☆441Updated 8 months ago
- ☆32Updated 4 months ago
- Steering Llama 2 with Contrastive Activation Addition☆129Updated 10 months ago
- ☆34Updated 3 weeks ago
- ☆124Updated this week
- Extract full next-token probabilities via language model APIs☆233Updated last year
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆100Updated 4 months ago
- This repository collects all relevant resources about interpretability in LLMs☆327Updated 4 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆71Updated 3 months ago