davidbau / baukit
☆184Updated 10 months ago
Alternatives and similar repositories for baukit:
Users that are interested in baukit are comparing it to the libraries listed below
- Function Vectors in Large Language Models (ICLR 2024)☆131Updated 3 months ago
- Using sparse coding to find distributed representations used by neural networks.☆207Updated last year
- ☆201Updated 3 months ago
- A resource repository for representation engineering in large language models☆90Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆113Updated 7 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆82Updated this week
- ☆106Updated 5 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆61Updated 2 months ago
- AI Logging for Interpretability and Explainability🔬☆97Updated 7 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆85Updated last year
- ☆82Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakers☆174Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆78Updated last month
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆493Updated 3 months ago
- ☆75Updated 5 months ago
- ☆131Updated 3 months ago
- ☆85Updated last year
- Algebraic value editing in pretrained language models☆62Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆111Updated last year
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆77Updated last year
- ☆104Updated last month
- A library for efficient patching and automatic circuit discovery.☆46Updated last month
- ☆135Updated this week
- ☆61Updated last year
- ☆114Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆176Updated last month
- Sparse probing paper full code.☆53Updated last year
- Landing Page for TOFU☆107Updated 3 weeks ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆89Updated 3 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆209Updated 5 months ago