Skip to content

Towards a fuller understanding of neurons with Clustered Compositional Explanations

Abstract

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations used to check the alignment (i.e., the highest ones), thus lacking completeness. In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neuron behavior. We define, and address the problems connected to the application of these methods to multiple ranges of activations, analyze the insights retrievable by using our algorithm, and propose some desiderata qualities that can be used to study the explanations returned by different algorithms.

Authors

*External Authors

Venue

NeurIPS 2023

Date

2023

Share

Related Publications

Join Us on the Cutting-Edge of AI Innovation