PAIR.withgoogle.com and friend's work on interpretability methods
☆234Jun 22, 2026Updated last month
Alternatives and similar repositories for interpretability
Users that are interested in interpretability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆223Oct 14, 2025Updated 9 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated last year
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆62May 9, 2023Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆267Feb 27, 2026Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆734Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- This repository collects all relevant resources about interpretability in LLMs☆402Nov 1, 2024Updated last year
- ☆67May 18, 2023Updated 3 years ago
- ☆14Apr 27, 2022Updated 4 years ago
- ☆19Mar 5, 2024Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆605Aug 7, 2025Updated 11 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,712Updated this week
- Training Sparse Autoencoders on Language Models☆1,484Updated this week
- ADAG: Transluce's MLP neuron-level circuit tracing library☆34Apr 10, 2026Updated 3 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆428Aug 21, 2025Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆424Jun 13, 2025Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆103Sep 5, 2021Updated 4 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆998Updated this week
- ☆293Oct 1, 2024Updated last year
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆40Aug 20, 2025Updated 11 months ago
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- ☆287Mar 2, 2024Updated 2 years ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆21Oct 24, 2025Updated 9 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆13Jan 26, 2025Updated last year
- Code for the experiments and websites of the paper "Same Task, Different Circuits"☆36Updated this week
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆25Mar 10, 2025Updated last year
- ☆211Nov 17, 2024Updated last year
- ☆257Feb 22, 2024Updated 2 years ago
- ☆13Jul 26, 2023Updated 3 years ago
- Code for 'The Geometry of Categorical and Hierarchical Concepts in Large Language Models' (ICLR 2025, Oral)☆115Feb 11, 2025Updated last year
- A framework for evaluating Machine Translation models.☆13Apr 21, 2026Updated 3 months ago
- ☆44Feb 11, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆178May 1, 2026Updated 2 months ago
- Engine for collecting, uploading, and downloading model activations☆30Apr 2, 2025Updated last year
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆125Feb 11, 2025Updated last year
- Code for reproducing experiments in our ACL 2019 paper "Probing Neural Network Comprehension of Natural Language Arguments"☆54Jun 21, 2022Updated 4 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆303Jul 20, 2024Updated 2 years ago
- Improving Alignment and Robustness with Circuit Breakers☆266Sep 24, 2024Updated last year
- A curated reading list for researchers in the Philosophy of Interpretability☆17Aug 17, 2025Updated 11 months ago