Official implementation of MAIA, A Multimodal Automated Interpretability Agent
☆112Oct 22, 2025Updated 9 months ago
Alternatives and similar repositories for maia
Users that are interested in maia are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Nearest Neighbor Normalization (EMNLP 2024)☆21Nov 1, 2024Updated last year
- Official implementation of FIND (NeurIPS '23) Function Interpretation Benchmark and Automated Interpretability Agents☆52Sep 24, 2024Updated last year
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆199Sep 26, 2025Updated 10 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Unified access to Large Language Model modules using NNsight☆116Updated this week
- Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning☆24Sep 9, 2024Updated last year
- Code for "Don't trust your eyes: on the (un)reliability of feature visualizations" (ICML 2024)☆34Nov 15, 2023Updated 2 years ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆380Jul 23, 2025Updated last year
- ☆15Jul 12, 2024Updated 2 years ago
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.☆20Jan 28, 2026Updated 6 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆29Nov 20, 2024Updated last year
- This repo contains the official implementation of ICCV 2025 paper "MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised L…☆22Sep 12, 2025Updated 10 months ago
- Attribute statements generated by LLMs to preceding tokens using attention weights.☆28Apr 22, 2025Updated last year
- 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.
- Official PyTorch Implementation for the "What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-mod…☆20Sep 26, 2024Updated last year
- This repository contains the code used for the experiments in the paper "Language Models use Lookbacks to Track Beliefs".☆16Mar 14, 2026Updated 4 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆250Mar 16, 2026Updated 4 months ago
- The AI that helps you achieve your goals☆11Feb 4, 2024Updated 2 years ago
- Code used for "Training Agents to Self-Report Misbehavior"☆18Feb 27, 2026Updated 5 months ago
- A tiny easily hackable implementation of a feature dashboard.☆17Oct 21, 2025Updated 9 months ago
- GPU_AC: Fast GPU Based Arithmetic Coding☆15Feb 26, 2025Updated last year
- awesome SAE papers☆79May 24, 2025Updated last year
- ☆18May 25, 2023Updated 3 years 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.
- 👋 Overcomplete is a Vision-based SAE Toolbox☆148Dec 4, 2025Updated 7 months ago
- James' cookbook of evaluations and finetuning experiments☆32Feb 19, 2026Updated 5 months ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆36Jun 5, 2025Updated last year
- [ACL 2025 Findings] Official pytorch implementation of "Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vis…☆25Jul 21, 2024Updated 2 years ago
- ☆223Oct 14, 2025Updated 9 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Explaining ML models using LLMs☆25Oct 21, 2024Updated last year
- [CVPR 2025] Concept Bottleneck Autoencoder (CB-AE) -- efficiently transform any pretrained (black-box) image generative model into an int…☆21Jul 13, 2026Updated 2 weeks ago
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- 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.
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆29Nov 3, 2025Updated 8 months ago
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- ☆28Sep 3, 2025Updated 10 months ago
- ☆257Feb 22, 2024Updated 2 years ago
- ☆179May 1, 2026Updated 2 months ago
- This is the official implementation of the Concept Discovery Models paper.☆15Aug 27, 2023Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,489Updated this week