montemac / activation_additions
Algebraic value editing in pretrained language models
☆63Updated last year
Alternatives and similar repositories for activation_additions:
Users that are interested in activation_additions are comparing it to the libraries listed below
- A library for efficient patching and automatic circuit discovery.☆57Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆29Updated 9 months ago
- Steering Llama 2 with Contrastive Activation Addition☆126Updated 9 months ago
- ☆80Updated 7 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆69Updated last week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆91Updated last year
- ☆22Updated 3 weeks ago
- ☆61Updated 4 months ago
- Sparse probing paper full code.☆55Updated last year
- General-purpose activation steering library☆50Updated 2 months ago
- ☆92Updated last year
- 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
- 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
- ☆113Updated 7 months ago
- Sparse Autoencoder Training Library☆42Updated 4 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated 3 weeks ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆161Updated this week
- ☆37Updated last year
- ☆68Updated this week
- ☆149Updated last week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 2 months ago
- ☆38Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆73Updated last year
- ☆18Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated 11 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆144Updated 5 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆66Updated 9 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆41Updated 5 months ago