Understanding a neural model can take many forms. For instance, we might want to know when and how the system relies on sensitive or spurious features, identify systematic errors in its predictions, or learn how to modify the training data and model architecture to improve accuracy and robustness. Today, answering these types of questions often involves significant human effort—researchers must formalize their question, formulate hypotheses about a model’s decision-making process, design datasets on which to evaluate model behavior, then use these datasets to refine and validate hypotheses. As a result, this type of understanding is slow and expensive to obtain, even about the most widely used models.
Automated Interpretability approaches have begun to address the issue of scale. Recently, such approaches have used pretrained language models like GPT-4 (in Bills et al. 2023) or Claude (in Bricken et al. 2023) to generate feature explanations. In earlier work, we introduced MILAN (Hernandez et al. 2022), a captioner model trained on human feature annotations that takes as input a feature visualization and outputs a description of that feature. But automated approaches that use learned models to label features leave something to be desired: they are primarily tools for one-shot hypothesis generation (Huang et al. 2023) rather than causal explanation, they characterize behavior on a limited set of inputs, and they are often low precision.
We introduce the Multimodal Automated Interpretability Agent (MAIA), aiming to help users understand models. MAIA combines the scalability of automated techniques with the flexibility of human experimentation—It iteratively generates hypotheses, runs experiments that test these hypotheses, observes experimental outcomes, and updates hypotheses until it can answer the user query. MAIA is based on the recent success of our Automated Interpretability Agent (AIA) paradigm (Schwettmann et al. 2023) where an LM-based agent interactively probes systems to explain their behavior. We expand this by equipping MAIA with a vision-language model backbone and an API of tools for designing experiments on other systems [add a link to the webpage section describing the tools]. With simple modifications to the user query to the agent, the same modular system can field both "macroscopic" questions like identifying systematic biases in model predictions (see the tench example above), as well as "microscopic" questions like describing individual features (see example below).
Our current line of research aims to build tools that help users understand models, while combining the flexibility of human experimentation with the scalability of automated techniques. We introduce the Multimodal Automated Interpretability Agent (MAIA), which designs experiments to answer user queries about components of AI systems. MAIA iteratively generates hypotheses, runs experiments that test these hypotheses, observes experimental outcomes, and updates hypotheses until it can answer the user query. MAIA builds on the Automated Interpretability Agent (AIA) paradigm we introduced in Schwettmann et al. 2023, where an LM-based agent interactively probes systems to explain their behavior. MAIA is equipped with a vision-language model backbone and an API of tools for designing interpretability experiments. With simple modifications to the user query to the agent, the same modular system can field both "macroscopic" questions like identifying systematic biases in model predictions (see the tench example above), as well as "microscopic" questions like describing individual features (see example below).
- We introduce 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. + 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.
MAIA uses the dataset_exemplars tool to compute images from the ImageNet dataset that maixmally activate a given system (in this case, an individual neuron). The dataset_exemplars tool returns masked versions of the images highlighting image subregions that maximally activate the neuron, as well as the activation value.
dataset_exemplars
MAIA uses the dataset_exemplars tool to compute images from the ImageNet dataset that maximally activate a given system (in this case, an individual neuron). The dataset_exemplars tool returns masked versions of the images highlighting image subregions that maximally activate the neuron, as well as the activation value.
In addition to using real-world stimuli as inputs to the system it is trying to interpret, MAIA can generate additional synthetic inputs that test specific dimensions of a system's selectivity. MAIA uses the text2image function to call a pretrained text-guided diffusion model on prompts it writes. These prompts can test specific hypotheses about the neuron's selectivities, such as in the example of the tennis ball neuron below.
text2image
MAIA can also call the edit_images tool which uses an text-based image editing module (Instruct Pix2Pix) to make image edits according to prompts written by MAIA. MAIA uses this tool to causally intervene on input space in order to test specific hypotheses about system behavior (e.g. whether the presence of a certain feature is required for the observed behavior!)
edit_images
Learned spurious features impose a challenge when machine learning models are applied in real-world scenarios, where test distributions can differ from training set statistics. We use MAIA to identify and remove learned spurious features inside a classification network (ResNet-18 trained on Spawrious, a synthetically generated dataset involving four dog breeds with different backgrounds). In the train set, each dog breed is spuriously correlated with a certain background (e.g. snow, jungle, desert, beach) while in the test set, the breed-background pairings are scrambled. We use MAIA to find a subset of final layer neurons that robustly predict a single dog breed independently of spurious features, simply by changing the query in the user prompt (see paper for more experimental details). Below, see an example neuron that MAIA determines to be selective for spurious correlations between dog breed and background: