jacobdunefsky / transcoder_circuitsLinks
☆154Updated 8 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:
- Using sparse coding to find distributed representations used by neural networks.☆261Updated last year
- ☆183Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆167Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- ☆233Updated 10 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated last week
- ☆107Updated 2 weeks ago
- ☆121Updated 11 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- ☆220Updated last year
- ☆177Updated 8 months ago
- ☆50Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆73Updated last week
- General-purpose activation steering library☆85Updated 2 months ago
- ☆320Updated 2 weeks ago
- Sparse probing paper full code.☆58Updated last year
- ☆87Updated 11 months ago
- ☆103Updated 5 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆172Updated 3 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆257Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 9 months ago
- ☆45Updated last week
- Algebraic value editing in pretrained language models☆65Updated last year
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆48Updated last year
- ☆96Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆246Updated last month
- ☆503Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆123Updated last year