EleutherAI / sae-auto-interp
☆99Updated this week
Related projects ⓘ
Alternatives and complementary repositories for sae-auto-interp
- ☆102Updated last month
- ☆43Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆157Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆60Updated last month
- ☆108Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆181Updated 11 months ago
- ☆99Updated 3 months ago
- ☆141Updated 2 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆69Updated this week
- Mechanistic Interpretability Visualizations using React☆195Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆94Updated 5 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆117Updated last month
- Sparse autoencoders☆333Updated 2 weeks ago
- ☆186Updated last month
- Sparse and discrete interpretability tool for neural networks☆53Updated 8 months ago
- ☆96Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆187Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- Sparse Autoencoder Training Library☆26Updated last week
- ☆24Updated 7 months ago
- ☆70Updated 3 months ago
- Erasing concepts from neural representations with provable guarantees☆208Updated 3 weeks ago
- ☆75Updated 9 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆17Updated 10 months ago
- Universal Neurons in GPT2 Language Models☆26Updated 5 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆116Updated 3 weeks ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆61Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago