hannamw / EAP-IG
☆21Updated 2 weeks ago
Alternatives and similar repositories for EAP-IG:
Users that are interested in EAP-IG are comparing it to the libraries listed below
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆56Updated 3 weeks ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated 11 months ago
- Sparse probing paper full code.☆55Updated last year
- ☆80Updated 7 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆40Updated 5 months ago
- ☆62Updated this week
- Algebraic value editing in pretrained language models☆63Updated last year
- Sparse Autoencoder Training Library☆42Updated 4 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆90Updated 3 years ago
- ☆60Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆125Updated 9 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆69Updated this week
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆50Updated 3 months ago
- ☆89Updated last year
- How do transformer LMs encode relations?☆46Updated last year
- AI Logging for Interpretability and Explainability🔬☆105Updated 9 months ago
- ☆38Updated last year
- ☆148Updated this week
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆22Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 9 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- ☆88Updated last month
- ☆47Updated last year
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆59Updated last year
- ☆37Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆95Updated this week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆22Updated 5 months ago