PAIR-code / interpretabilityLinks
PAIR.withgoogle.com and friend's work on interpretability methods
☆192Updated 2 weeks ago
Alternatives and similar repositories for interpretability
Users that are interested in interpretability are comparing it to the libraries listed below
Sorting:
- ☆226Updated 8 months ago
- Utilities for the HuggingFace transformers library☆68Updated 2 years ago
- ☆121Updated last year
- ☆97Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- ☆212Updated last year
- The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.☆177Updated 3 years ago
- ☆76Updated 3 months ago
- A library for finding knowledge neurons in pretrained transformer models.☆158Updated 3 years ago
- ☆101Updated 2 weeks ago
- Sparse probing paper full code.☆58Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- A library for efficient patching and automatic circuit discovery.☆66Updated 2 months ago
- ☆62Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated last year
- How do transformer LMs encode relations?☆48Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆131Updated 7 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆54Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆43Updated 6 months ago
- ☆119Updated 10 months ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 4 months ago
- ☆54Updated 2 years ago
- ☆67Updated 2 years ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆93Updated 3 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- ☆84Updated 10 months ago