Decompose the model: Mechanistic interpretability in image models with
Generalized Integrated Gradients (GIG)
Decompose the model: Mechanistic interpretability in image models with
Generalized Integrated Gradients (GIG)
In the field of eXplainable AI (XAI) in language models, the progression from local explanations of individual decisions to global explanations with high-level concepts has laid the groundwork for mechanistic interpretability, which aims to decode the exact operations. However, this paradigm has not been adequately explored in image models, where …