Interpretability Illusions in the Generalization of Simplified Models

6 December 2023

Papers citing "Interpretability Illusions in the Generalization of Simplified Models"

6 / 6 papers shown

Title
Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii Kola Ayonrinde Louis Jaburi XAI 85 1 0 02 May 2025
LangVAE and LangSpace: Building and Probing for Language Model VAEs Danilo S. Carvalho Yingji Zhang Harriet Unsworth André Freitas 36 0 0 29 Mar 2025
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model Michael Hanna Ollie Liu Alexandre Variengien LRM 193 121 0 30 Apr 2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models Mor Geva Jasmijn Bastings Katja Filippova Amir Globerson KELM 191 266 0 28 Apr 2023
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Kevin Wang Alexandre Variengien Arthur Conmy Buck Shlegeris Jacob Steinhardt 212 497 0 01 Nov 2022
In-context Learning and Induction Heads Catherine Olsson Nelson Elhage Neel Nanda Nicholas Joseph Nova Dassarma ... Tom B. Brown Jack Clark Jared Kaplan Sam McCandlish C. Olah 250 463 0 24 Sep 2022