Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation

ArXi:2603.19742v1 Announce Type: new Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effective operation. While recent efforts have yielded a plethora of attribution methods attempting to balance faithfulness and computational efficiency, dense component attribution remains prohibitively expensive. In this work, we