DePass: Unified Feature Attributing by Simple Decomposed Forward Pass

Xiangyu Hong, Che Jiang, Kai Tian, Biqing Qi, Youbang Sun, Ning Ding, Bowen Zhou

Keywords: Attribution, Mechanistic Interpretability, Generative Models, Large Language Models

Abstract: Attributing the behavior of Transformer models to internal computations is a central challenge in mechanistic interpretability. We introduce DePass, a unified framework for feature attribution based on a single decomposed forward pass. DePass decomposes hidden states into customized additive components, then propagates them with attention scores and MLP's activations fixed. It achieves faithful, fine-grained attribution without requiring auxiliary training. We validate DePass across token-level, model component-level, and subspace-level attribution tasks, demonstrating its effectiveness and fidelity. Our experiments highlight its potential to attribute information flow between arbitrary components of a Transformer model. We hope DePass serves as a foundational tool for broader applications in interpretability.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 16063