ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2211.04367
  4. Cited By
Much Easier Said Than Done: Falsifying the Causal Relevance of Linear
  Decoding Methods

Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods

8 November 2022
L. Hayne
Abhijit Suresh
Hunar Jain
Rahul Kumar
R. M. Carter
    FAtt
ArXivPDFHTML

Papers citing "Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods"

2 / 2 papers shown
Title
Selectivity considered harmful: evaluating the causal impact of class
  selectivity in DNNs
Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
Matthew L. Leavitt
Ari S. Morcos
52
33
0
03 Mar 2020
Revisiting the Importance of Individual Units in CNNs via Ablation
Revisiting the Importance of Individual Units in CNNs via Ablation
Bolei Zhou
Yiyou Sun
David Bau
Antonio Torralba
FAtt
56
116
0
07 Jun 2018
1