An LLM agent framework for automated AI interpretability research
☆20Apr 17, 2026Updated 7 months ago
Alternatives and similar repositories for AutoInterp
Users that are interested in AutoInterp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ADAG: Transluce's MLP neuron-level circuit tracing library☆50Apr 10, 2026Updated 7 months ago
- Public-facing repository for starter code related to in-class demos, homeworks, and projects in Tufts' Intro to ML course for fall 2020☆10Dec 8, 2020Updated 5 years ago
- Official Repository for Frame Representation Hypothesis paper☆10Oct 26, 2026Updated 3 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- @Stanford University's iOS app development course.☆12Oct 10, 2024Updated 2 years ago
- 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.
- ☆13Jan 28, 2023Updated 3 years ago
- Terminal-Bench 4.0 tasks ported to Karotte, with fixes to ambiguous instructions and grader bugs.☆13Updated this week
- ☆17May 21, 2026Updated 5 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆79Jun 23, 2025Updated last year
- ☆13Oct 24, 2026Updated 3 weeks ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.☆31Jul 8, 2026Updated 4 months ago
- Dataset Generation Code for SimpleStories☆12Dec 19, 2025Updated 11 months ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- ☆89Feb 25, 2025Updated last year
- 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.
- dfa + trie + smolLM-135M based prefix autocompletion☆12Sep 2, 2025Updated last year
- ☆10Aug 14, 2023Updated 3 years ago
- A Minimalistic Search Agent☆83May 12, 2026Updated 6 months ago
- ☆15Dec 12, 2024Updated last year
- Roundtable with transcripts / newsletters of Lenny Rachitsky☆12Mar 18, 2026Updated 8 months ago
- ☆10Dec 6, 2022Updated 3 years ago
- ☆16Jul 17, 2026Updated 4 months ago
- A framework for testing and evaluating AI agents across various task domains, designed for misalignment interpretability research.☆36Sep 17, 2026Updated 2 months ago
- 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…☆14Jan 26, 2025Updated last year
- 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.
- ☆14Aug 14, 2023Updated 3 years ago
- A python implementation of a simple Unit Selection Text-to-Speech (TTS) synthesis system. It works with CMU-Arctic data by default☆11Mar 14, 2015Updated 11 years ago
- LLM play 20questions with itself☆13Mar 31, 2023Updated 3 years ago
- ☆14Jan 2, 2026Updated 10 months ago
- ☆10Nov 28, 2023Updated 2 years ago
- diffusers with search engine☆12Updated this week
- Complex Reasoning with ReAct and LangChain☆12Apr 24, 2024Updated 2 years ago
- Training Qwen 2.5 1.5B Instruct with SFT and RLVR (GRPO) on the GSM8K dataset, analyzing performance across GSM8K and MATH benchmarks.☆13Mar 3, 2026Updated 8 months ago
- JIRA integration server for Model Context Protocol (MCP) - enables LLMs to interact with JIRA tasks and workflows☆10Apr 3, 2026Updated 7 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.
- Example code using the DSPy framework.☆21May 30, 2024Updated 2 years ago
- No-chain-of-thought reasoning benchmark (NCRI): sealed banks, no-CoT runner with witnesses, frozen placement, scores for 285 models☆29Nov 9, 2026Updated last week
- VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation [TMLR26]☆15Jun 1, 2026Updated 5 months ago
- A vanilla implementation of ReAct: Synergizing Reasoning and Acting in Language Models☆18Sep 2, 2026Updated 2 months ago
- A tool to assist in the interpretation of learned features in sparse autoencoders (in particular the four SAE's trained by Joseph Bloom o…☆19Oct 4, 2024Updated 2 years ago
- ☆14Feb 12, 2026Updated 9 months ago
- LLM-driven proof search on Erdős problems (2 solutions accepted on erdosproblems.com)☆17Apr 21, 2026Updated 6 months ago
Are these results useful?