anthropics / evalsLinks
☆301Updated last year
Alternatives and similar repositories for evals
Users that are interested in evals are comparing it to the libraries listed below
Sorting:
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- METR Task Standard☆161Updated 8 months ago
- ☆138Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆92Updated last year
- ☆242Updated 2 years ago
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆211Updated 4 months ago
- ☆276Updated last year
- ☆102Updated 5 months ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆203Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- RuLES: a benchmark for evaluating rule-following in language models☆234Updated 7 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆530Updated last month
- ☆242Updated last year
- ☆127Updated last year
- Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"☆321Updated last year
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898☆224Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆118Updated last year
- Used for adaptive human in the loop evaluation of language and embedding models.☆311Updated 2 years ago
- ☆104Updated last week
- Erasing concepts from neural representations with provable guarantees☆237Updated 8 months ago
- ☆295Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Collection of evals for Inspect AI☆241Updated this week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- [ICLR 2024 Spotlight] FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets☆218Updated last year