explanare / ravelLinks
Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
☆56Updated last year
Alternatives and similar repositories for ravel
Users that are interested in ravel are comparing it to the libraries listed below
Sorting:
- 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
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- [ICLR 2025] General-purpose activation steering library☆111Updated last month
- ☆92Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆82Updated 7 months ago
- ☆57Updated 3 months ago
- ☆18Updated 2 months ago
- ☆48Updated 2 years ago
- ☆98Updated last year
- ☆107Updated 8 months ago
- ☆131Updated this week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- Forcing Diffuse Distributions out of Language Models☆17Updated last year
- AI Logging for Interpretability and Explainability🔬☆129Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆188Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- Sparse probing paper full code.☆62Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- ☆29Updated last year
- Algebraic value editing in pretrained language models☆66Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 11 months ago
- ☆179Updated 11 months ago
- ☆56Updated 2 years ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆61Updated 2 years ago
- ☆28Updated 8 months ago
- ☆190Updated last week