Learned feature representations are biased by complexity, learning order, position, and more

9 May 2024

Papers citing "Learned feature representations are biased by complexity, learning order, position, and more"

9 / 9 papers shown

Title
What Representational Similarity Measures Imply about Decodable Information Sarah E. Harvey David Lipshutz Alex H. Williams 31 1 0 12 Nov 2024
Understanding Visual Feature Reliance through the Lens of Complexity Thomas Fel Louis Bethune Andrew Kyle Lampinen Thomas Serre Katherine Hermann FAtt CoGe 25 6 0 08 Jul 2024
Survival of the Fittest Representation: A Case Study with Modular Addition Xiaoman Delores Ding Zifan Carl Guo Eric J. Michaud Ziming Liu Max Tegmark 29 3 0 27 May 2024
Decomposing and Editing Predictions by Modeling Model Computation Harshay Shah Andrew Ilyas A. Madry KELM 28 14 0 17 Apr 2024
Task structure and nonlinearity jointly determine learned representational geometry Matteo Alleman Jack W. Lindsey Stefano Fusi 30 8 0 24 Jan 2024
Interpretability Illusions in the Generalization of Simplified Models Dan Friedman Andrew Kyle Lampinen Lucas Dixon Danqi Chen Asma Ghandeharioun 12 14 0 06 Dec 2023
Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates Miao Lu Beining Wu Xiaodong Yang Difan Zou MLT 37 2 0 26 Oct 2023
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations Atticus Geiger Zhengxuan Wu Christopher Potts Thomas F. Icard Noah D. Goodman CML 73 98 0 05 Mar 2023
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 240 453 0 24 Sep 2022