callummcdougall / sae_vis
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
☆133Updated last month
Related projects: ⓘ
- Training Sparse Autoencoders on Language Models☆367Updated this week
- Mechanistic Interpretability Visualizations using React☆175Updated 2 months ago
- ☆99Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆162Updated 10 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆173Updated last month
- Sparse autoencoders☆297Updated last week
- ☆110Updated 3 weeks ago
- ☆75Updated this week
- ☆174Updated 4 months ago
- ☆54Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆52Updated last month
- ☆24Updated 5 months ago
- ☆33Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆83Updated 3 months ago
- ☆91Updated last month
- ☆267Updated 2 months ago
- This repository collects all relevant resources about interpretability in LLMs☆230Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆356Updated this week
- Extract full next-token probabilities via language model APIs☆226Updated 6 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆76Updated 3 weeks ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (2024)☆169Updated 3 months ago
- Erasing concepts from neural representations with provable guarantees☆202Updated 3 months ago
- Understand and test language model architectures on synthetic tasks.☆156Updated 4 months ago
- Improving Alignment and Robustness with Circuit Breakers☆124Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆73Updated 11 months ago
- ☆159Updated 6 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆185Updated 7 months ago
- ☆91Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆57Updated last week
- Sparse probing paper full code.☆47Updated 9 months ago