all AI news
Interpreting Grokked Transformers in Complex Modular Arithmetic
Feb. 28, 2024, 5:43 a.m. | Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo
cs.LG updates on arXiv.org arxiv.org
Abstract: Grokking has been actively explored to reveal the mystery of delayed generalization. Identifying interpretable algorithms inside the grokked models is a suggestive hint to understanding its mechanism. In this work, beyond the simplest and well-studied modular addition, we observe the internal circuits learned through grokking in complex modular arithmetic via interpretable reverse engineering, which highlights the significant difference in their dynamics: subtraction poses a strong asymmetry on Transformer; multiplication requires cosine-biased components at all the …
abstract algorithms arxiv beyond cs.ai cs.lg inside modular observe through transformers type understanding work
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
2 days, 13 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne