We Can't Understand AI Using our Existing Vocabulary

11 February 2025

Papers citing "We Can't Understand AI Using our Existing Vocabulary"

5 / 5 papers shown

Title
Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining Deniz Bayazit Aaron Mueller Antoine Bosselut 0 0 0 05 Sep 2025
Foundations of Interpretable Models Pietro Barbiero M. Zarlenga Alberto Termine M. Jamnik Giuseppe Marra AI4CE 41 0 0 01 Aug 2025
A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i Kola Ayonrinde Louis Jaburi MILM 256 2 0 01 May 2025
MIB: A Mechanistic Interpretability Benchmark Aaron Mueller Atticus Geiger Sarah Wiegreffe Dana Arad Iván Arcuschin ... Alessandro Stolfo Martin Tutek Amir Zur David Bau Yonatan Belinkov 239 4 0 17 Apr 2025
Page Classification for Print Imaging Pipeline Shaoyuan Xu Cheng Lu Mark Shaw Peter Bauer J. Allebach VLM 138 1 0 03 Apr 2025