# A Multimodal Automated Interpretability Agent

arXiv: https://arxiv.org/abs/2404.14394 · HTML: https://mlsanity.com/paper/2404.14394/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 66 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification](https://mlsanity.com/paper/2211.11158/) (2022)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Visualizing and Understanding Recurrent Networks](https://mlsanity.com/paper/1506.02078/) (2015)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)

## Built on by (most cited first, 30 of 63)

- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [What's in the Image? A Deep-Dive into the Vision of Vision Language Models](https://mlsanity.com/paper/2411.17491/) (2024)
- [Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models](https://mlsanity.com/paper/2405.13872/) (2024)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Building Production-Ready Probes For Gemini](https://mlsanity.com/paper/2601.11516/) (2026)
- [When Models Manipulate Manifolds: The Geometry of a Counting Task](https://mlsanity.com/paper/2601.04480/) (2026)
- [Interpreting the linear structure of vision-language model embedding spaces](https://mlsanity.com/paper/2504.11695/) (2025)
- [SketchAgent: Language-Driven Sequential Sketch Generation](https://mlsanity.com/paper/2411.17673/) (2024)
- [Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences](https://mlsanity.com/paper/2510.13900/) (2025)
- [InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques](https://mlsanity.com/paper/2407.14494/) (2024)
- [Because we have LLMs, we Can and Should Pursue Agentic Interpretability](https://mlsanity.com/paper/2506.12152/) (2025)
- [Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants](https://mlsanity.com/paper/2512.15712/) (2025)
- [Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors](https://mlsanity.com/paper/2505.11770/) (2025)
- [The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching](https://mlsanity.com/paper/2606.27510/) (2026)
- [HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks](https://mlsanity.com/paper/2503.10894/) (2025)
- [Learning on Model Weights using Tree Experts](https://mlsanity.com/paper/2410.13569/) (2024)
- [Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning](https://mlsanity.com/paper/2505.24360/) (2025)
- [Enhancing Concept Localization in CLIP-based Concept Bottleneck Models](https://mlsanity.com/paper/2510.07115/) (2025)
- [Meta-Models: An Architecture for Decoding LLM Behaviors Through Interpreted Embeddings and Natural Language](https://mlsanity.com/paper/2410.02472/) (2024)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain](https://mlsanity.com/paper/2512.08560/) (2025)
- [Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers](https://mlsanity.com/paper/2504.20902/) (2025)
- [Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads](https://mlsanity.com/paper/2505.17425/) (2025)
- [Evaluating Neuron Explanations: A Unified Framework with Sanity Checks](https://mlsanity.com/paper/2506.05774/) (2025)
- [Measuring Sparse Autoencoder Feature Sensitivity](https://mlsanity.com/paper/2509.23717/) (2025)
- [Learning Concept Bottleneck Models from Mechanistic Explanations](https://mlsanity.com/paper/2603.07343/) (2026)
- [The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models](https://mlsanity.com/paper/2603.22278/) (2026)
- [Automated Interpretability and Feature Discovery in Language Models with Agents](https://mlsanity.com/paper/2605.01555/) (2026)

## Abstract (arXiv)

This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. We evaluate applications of MAIA to computer vision models. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. Across several trained models and a novel dataset of synthetic vision neurons with paired ground-truth descriptions, MAIA produces descriptions comparable to those generated by expert human experimenters. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified.