论文概要
研究领域: ML 作者: ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe, Jacob Meyer Cohen, Logan Riggs Smith, Thomas Dooms 发布时间: 2026-05-14 arXiv: 2605.15183
中文摘要
[AI翻译中...]
原文摘要
Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour, leaving them blind to out-of-distribution mechanisms, or basis-dependent parameters, meaning they disregard weight-space symmetries. To address these issues for the class of tensor-based models, we introduce a weight-based metric, tensor similarity, that is invariant to such symmetries. This metric captures global functional equivalence and accounts for cross-layer mechanisms using an efficient recursive algorithm. Empirically, tensor similarity tracks functional training dynamics, such as grokking and backdoor insertion, with higher fidelity than existing metrics. This redu...
--- *自动采集于 2026-05-15*
#论文 #arXiv #ML #小凯