Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Transformer-based language models have achieved notable success, yet their internal reasoning mechanisms remain largely opaque due to complex non-linear interactions and high-dimensional operations. While previous research suggests that these models implicitly encode reasoning structures, it is still unclear which specific multi-step thought processes they employ to solve complex tasks. To address this gap, we propose a novel mechanistic interpretability framework, SICAF, designed to trace and analyze the reasoning strategies that language models use in multi-step inference tasks. By employing circuit analysis and self-influence functions, we quantify the evolving importance of each token throughout the reasoning process, thereby mapping the pathways the model uses for inference. Applying SICAF to the GPT-2 model on the Indirect Object Identification (IOI) prediction task, we demonstrate how underlying circuits can reveal a reasoning process that aligns with human interpretability, offering new insights into the model's internal logic.