microsoft / mechanistic-error-probeLinks
A mechanistic approach for understanding and detecting factual errors of large language models.
☆49Updated 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
- Steering vectors for transformer language models in Pytorch / Huggingface☆137Updated 10 months ago
- ☆112Updated 10 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
- A library for efficient patching and automatic circuit discovery.☆84Updated 5 months ago
- ☆97Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆123Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆99Updated 2 years ago
- ☆80Updated last year
- Sparse and discrete interpretability tool for neural networks☆65Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆234Updated last week
- Functional Benchmarks and the Reasoning Gap☆90Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆204Updated last year
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆107Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆161Updated 6 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆132Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆233Updated last year
- Erasing concepts from neural representations with provable guarantees☆242Updated 11 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆222Updated 2 weeks ago
- Evaluating LLMs with fewer examples☆170Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆196Updated 10 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 2 months ago
- ☆149Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆189Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆95Updated 3 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆152Updated 11 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…☆78Updated last year
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆91Updated last year