jacobdunefsky / transcoder_circuitsLinks
☆173Updated 10 months ago
Alternatives and similar repositories for transcoder_circuits
Users that are interested in transcoder_circuits are comparing it to the libraries listed below
Sorting:
- ☆186Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆270Updated 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
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆154Updated this week
- ☆242Updated last year
- ☆125Updated 2 weeks ago
- ☆123Updated last year
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- ☆54Updated 10 months ago
- ☆199Updated 10 months ago
- ☆347Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- ☆91Updated last year
- [ICLR 2025] General-purpose activation steering library☆107Updated 2 weeks ago
- ☆51Updated 2 months ago
- ☆230Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆267Updated last year
- Sparse probing paper full code.☆61Updated last year
- ☆127Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆275Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆81Updated 7 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- Modified to support crosscoder training.☆23Updated 2 months ago