microsoft / mechanistic-error-probeLinks
A mechanistic approach for understanding and detecting factual errors of large language models.
☆46Updated last year
Alternatives and similar repositories for mechanistic-error-probe
Users that are interested in mechanistic-error-probe are comparing it to the libraries listed below
Sorting:
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- ☆101Updated 5 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆112Updated last year
- A library for efficient patching and automatic circuit discovery.☆70Updated 2 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆90Updated 8 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 7 months ago
- NeurIPS 2024 tutorial on LLM Inference☆45Updated 7 months ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆22Updated last year
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated 2 years ago
- ☆87Updated 11 months ago
- ☆29Updated last year
- PyTorch library for Active Fine-Tuning☆84Updated 4 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated 10 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- ☆72Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆99Updated 3 weeks ago
- ☆40Updated last month
- Functional Benchmarks and the Reasoning Gap☆88Updated 9 months ago
- Official implementation of FIND (NeurIPS '23) Function Interpretation Benchmark and Automated Interpretability Agents☆49Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆112Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆56Updated 8 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆44Updated 7 months ago
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆70Updated 2 years ago
- ☆35Updated 2 years ago
- PASTA: Post-hoc Attention Steering for LLMs☆121Updated 7 months ago
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆86Updated last year
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆25Updated 7 months ago