Dissecting Jet-Tagger Through Mechanistic Interpretability

ArXi:2605.09881v1 Announce Type: cross Mechanistic interpretability seeks to reverse engineer a trained neural network by identifying the minimal subset of internal components. We perform a mechanistic interpretability analysis of the Particle Transformer architecture, trained on the Top Quark Tagging reference dataset, with the goal of identifying the computational circuit responsible for jet classification and characterizing the physical content of its internal representations.