stanfordnlp / axbenchLinks
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
☆136Updated 3 months ago
Alternatives and similar repositories for axbench
Users that are interested in axbench are comparing it to the libraries listed below
Sorting:
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆40Updated 11 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- [ICLR 2025] General-purpose activation steering library☆108Updated 2 weeks ago
- AI Logging for Interpretability and Explainability🔬☆128Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- ☆91Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆187Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆117Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆26Updated 2 weeks ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- ☆52Updated 5 months ago
- ☆97Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- ☆174Updated 10 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆80Updated 7 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 8 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆158Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 10 months ago
- ☆41Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆64Updated 10 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- ☆125Updated 2 weeks ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆154Updated last week
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆190Updated 7 months ago
- ☆48Updated last year
- Test-time-training on nearest neighbors for large language models☆46Updated last year