A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine learning interpretability research that aims to reverse-engineer neural networks into understandable computational components.
☆156Sep 26, 2026Updated this week
Alternatives and similar repositories for awesome-mechanistic-interpretability
Users that are interested in awesome-mechanistic-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:
- A repository for awesome resources in mechanistic interpretability☆17Jan 18, 2023Updated 3 years ago
- A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository agg…☆220Mar 4, 2026Updated 6 months ago
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year
- The Github repo for our survey paper: "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large…☆157Apr 15, 2026Updated 5 months ago
- A longitudinal dataset for academic literature, including papers, metadata, and citation graphs, Also available on 🤗 HuggingFace and Kag…☆18Sep 6, 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.
- A library for mechanistic interpretability of GPT-style language models☆3,911Updated this week
- open source interpretability platform 🧠☆1,148Updated this week
- [ICML 2025 Poster] SAE-V: Interpreting Multimodal Models for Enhanced Alignment☆18Jun 5, 2025Updated last year
- A curated list of resources for activation engineering☆141Oct 2, 2025Updated 11 months ago
- The NDIF server, which performs deep inference and serves nnsight requests remotely☆52Sep 15, 2026Updated last week
- Fine Tuning Multimodal LLM "Idefics 9B" on Pokemon Go Dataset available on Hugging Face.☆18Jan 15, 2024Updated 2 years ago
- Small Multimodal Vision Model "Imp-v1-3b" trained using Phi-2 and Siglip.☆17Feb 5, 2024Updated 2 years ago
- Minimal implementation of Rectified Flows diffusion models to generate a dino shape from the datasaurus dataset.☆17Feb 9, 2026Updated 7 months ago
- Code for Negation Neglect☆18May 22, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code for "A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models"☆17Jul 20, 2025Updated last year
- Parameter Decomposition☆144Updated this week
- [NeurIPS2024] Official code for (IMA) Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs☆23Oct 15, 2024Updated last year
- ☆102Apr 18, 2026Updated 5 months ago
- Code for the experiments and websites of the paper "Same Task, Different Circuits"☆37Jul 21, 2026Updated 2 months ago
- Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces☆42Aug 21, 2026Updated last month
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆14May 2, 2025Updated last year
- Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)☆22Oct 16, 2025Updated 11 months ago
- A Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization☆108Jul 30, 2026Updated last month
- 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.
- ☆12Jul 30, 2025Updated last year
- ☆14Apr 21, 2023Updated 3 years ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆60Nov 3, 2024Updated last year
- This is the source code for: Context-aware Entity Typing in Knowledge Graphs.☆16May 10, 2022Updated 4 years ago
- ☆28Aug 10, 2025Updated last year
- Resources for research teams running machine learning experiments.☆15Dec 10, 2025Updated 9 months ago
- ICIAP2022 - Learning Semantics for Visual Place Recognition through Multi-Scale Attention☆16May 10, 2022Updated 4 years ago
- ☆18May 5, 2021Updated 5 years ago
- How do transformer LMs encode relations?☆60Feb 24, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Siamese Capsule Networks for Face Verification☆11Mar 22, 2019Updated 7 years ago
- Repo of "Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems" (ACL 2026)☆32Apr 27, 2026Updated 5 months ago
- ☆18Feb 19, 2025Updated last year
- Training LLMs to Report Their Learned Behaviors☆29Apr 28, 2026Updated 4 months ago
- Grounding Language Models for Compositional and Spatial Reasoning☆18Oct 26, 2022Updated 3 years ago
- Code for the paper Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies (NeurIPS 2023). https://arxiv.or…☆15Nov 21, 2023Updated 2 years ago
- [NeurIPS 2025] TL;DR: Aligning pretrained unimodal models with the proposed framework using limited paired data yields ~52% gains in cros…☆24Feb 2, 2026Updated 7 months ago