IINemo / lm-polygraph
☆211Updated this week
Alternatives and similar repositories for lm-polygraph:
Users that are interested in lm-polygraph are comparing it to the libraries listed below
- AI Logging for Interpretability and Explainability🔬☆100Updated 7 months ago
- ☆187Updated 11 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆88Updated this week
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆156Updated 3 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆84Updated last year
- ☆136Updated this week
- ☆140Updated this week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆165Updated 3 months ago
- ☆202Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆120Updated 8 months ago
- Extract full next-token probabilities via language model APIs☆229Updated 11 months ago
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆184Updated 2 months ago
- ☆109Updated 5 months ago
- Official code repository for article Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts☆26Updated last year
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆173Updated 3 weeks ago
- Erasing concepts from neural representations with provable guarantees☆221Updated this week
- A toolkit for describing model features and intervening on those features to steer behavior.☆154Updated 2 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆135Updated 3 months ago
- ☆86Updated last year
- How do transformer LMs encode relations?☆46Updated 11 months ago
- Sparse probing paper full code.☆54Updated last year
- ☆45Updated this week
- A library for efficient patching and automatic circuit discovery.☆48Updated 2 months ago
- Using sparse coding to find distributed representations used by neural networks.☆210Updated last year
- ☆75Updated 5 months ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆79Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆177Updated last month
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆127Updated 6 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆80Updated 2 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆65Updated 10 months ago