2 papers
cs.CL2025
From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits
Karim Saraipour, Shichang Zhang
Transformer-based language models (LMs) can perform a wide range of tasks, and mechanistic interpretability (MI) aims to reverse engineer the components responsible for task comple…
cs.LG2024
Generalized Group Data Attribution
Dan Ley, Suraj Srinivas, Shichang Zhang +2
Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noi…