HannahKirk / prism-alignment
The Prism Alignment Project
☆73Updated 11 months ago
Alternatives and similar repositories for prism-alignment:
Users that are interested in prism-alignment are comparing it to the libraries listed below
- ☆106Updated 11 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆115Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"☆54Updated 10 months ago
- ☆93Updated last year
- ☆50Updated 2 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated last year
- ☆82Updated 8 months ago
- ☆48Updated last year
- This repository contains data, code and models for contextual noncompliance.☆21Updated 9 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 4 months ago
- AI Logging for Interpretability and Explainability🔬☆111Updated 10 months ago
- ☆12Updated 10 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆114Updated 5 months ago
- ☆68Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆95Updated 2 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
- ☆43Updated 8 months ago
- ☆21Updated 10 months ago
- Steering Llama 2 with Contrastive Activation Addition☆143Updated 11 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆41Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆62Updated 2 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆43Updated 6 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆68Updated 10 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆99Updated last year
- Data and code for the Corr2Cause paper (ICLR 2024)☆96Updated last year
- Code/data for MARG (multi-agent review generation)☆42Updated 5 months ago
- Generating diverse counterfactual data for Natural Language Understanding tasks using Large Language Models (LLMs). The generator support…☆36Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆46Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated last month