Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

TL;DR

This paper introduces DN-CBM, a novel concept bottleneck model that automatically discovers and names concepts learned by models like CLIP, enabling more interpretable and task-agnostic concept representations for classification.

Contribution

The paper proposes a new approach that automatically discovers and names concepts without predefining them, improving interpretability and flexibility of concept bottleneck models.

Findings

Automatically discovers meaningful concepts across datasets

Assigns interpretable names to discovered concepts

Achieves competitive performance with interpretable models

Abstract

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for classification. Such models typically require first coming up with a set of concepts relevant to the task and then aligning the representations of a feature extractor to map to these concepts. However, even with powerful foundational feature extractors like CLIP, there are no guarantees that the specified concepts are detectable. In this work, we leverage recent advances in mechanistic interpretability and propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm: instead of pre-selecting concepts based on the downstream classification task, we use sparse autoencoders to first discover concepts learnt by the model, and then name them and train linear probes for classification. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model. We perform a comprehensive evaluation across multiple datasets and CLIP architectures and show that our method yields semantically meaningful concepts, assigns appropriate names to them that make them easy to interpret, and yields performant and interpretable CBMs. Code available at https://github.com/neuroexplicit-saar/discover-then-name.