Using Captum to Explain Generative Language Models

Vivek Miglani, Aobo Yang, Aram H. Markosyan, Diego Garcia-Olano, Narine Kokhlikyan

Keywords: interpretability, explainability, LLM

Abstract: Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.

Submission Number: 27