PAIR-code / interpretabilityLinks
PAIR.withgoogle.com and friend's work on interpretability methods
☆189Updated last month
Alternatives and similar repositories for interpretability
Users that are interested in interpretability are comparing it to the libraries listed below
Sorting:
- Mechanistic Interpretability Visualizations using React☆251Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated this week
- ☆222Updated 8 months ago
- Utilities for the HuggingFace transformers library☆68Updated 2 years ago
- ☆121Updated last year
- ☆96Updated last month
- ☆96Updated 3 months ago
- ☆116Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆76Updated last year
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆54Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- Sparse probing paper full code.☆56Updated last year
- ☆75Updated 3 months ago
- ☆83Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- A library for finding knowledge neurons in pretrained transformer models.☆157Updated 3 years ago
- ☆209Updated last year
- ☆33Updated last week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆227Updated 4 months ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- How do transformer LMs encode relations?☆48Updated last year
- ☆62Updated 2 years ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆42Updated 6 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆493Updated 11 months ago