microsoft / mechanistic-error-probe
A mechanistic approach for understanding and detecting factual errors of large language models.
☆41Updated 8 months ago
Alternatives and similar repositories for mechanistic-error-probe:
Users that are interested in mechanistic-error-probe are comparing it to the libraries listed below
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆67Updated 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 10 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆103Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆73Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆129Updated 10 months ago
- ☆61Updated 4 months ago
- ☆89Updated last month
- ☆80Updated 7 months ago
- ☆34Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆41Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆149Updated last week
- ☆25Updated 7 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆163Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆71Updated 3 months ago
- The Prism Alignment Project☆69Updated 10 months ago
- Sparse and discrete interpretability tool for neural networks☆59Updated last year
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆69Updated 7 months ago
- ☆68Updated 11 months ago
- ☆26Updated 8 months ago
- NeurIPS 2024 tutorial on LLM Inference☆39Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆46Updated 4 months ago
- ☆124Updated this week
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated last year
- ☆38Updated last year
- ☆26Updated 11 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆112Updated last year