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:
- 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
- ☆78Updated last year
- ☆110Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆126Updated 8 months ago
- 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 release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆117Updated last year
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- ☆92Updated last year
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆95Updated 2 years ago
- PyTorch library for Active Fine-Tuning☆93Updated last month
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- ☆69Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated 11 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- PASTA: Post-hoc Attention Steering for LLMs☆126Updated 11 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- A repository for transformer critique learning and generation☆88Updated 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…☆75Updated last year
- Evaluating LLMs with fewer examples☆164Updated last year
- Erasing concepts from neural representations with provable guarantees☆238Updated 9 months ago
- ☆127Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆48Updated 11 months ago
- We develop benchmarks and analysis tools to evaluate the causal reasoning abilities of LLMs.☆130Updated last year
- ☆142Updated last month
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆107Updated 2 years ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆23Updated last year
- [COLM 2025] EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees☆25Updated 3 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆190Updated 8 months ago