ResearchTrend.AI
  • Communities
  • Connect sessions
  • AI calendar
  • Organizations
  • Join Slack
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2504.08729
  4. Cited By
Steering CLIP's vision transformer with sparse autoencoders

Steering CLIP's vision transformer with sparse autoencoders

11 April 2025
Sonia Joseph
Praneet Suresh
Ethan Goldfarb
Lorenz Hufe
Yossi Gandelsman
Robert Graham
Danilo Bzdok
Wojciech Samek
Blake A. Richards
ArXiv (abs)PDFHTML

Papers citing "Steering CLIP's vision transformer with sparse autoencoders"

9 / 9 papers shown
Title
MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
Jan Sobotka
Luca Baroni
Ján Antolík
OffRL
64
0
0
23 Oct 2025
From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
Praneet Suresh
Jack Stanley
Sonia Joseph
Luca Scimeca
Danilo Bzdok
104
1
0
08 Sep 2025
Towards Mechanistic Defenses Against Typographic Attacks in CLIP
Towards Mechanistic Defenses Against Typographic Attacks in CLIP
Lorenz Hufe
Constantin Venhoff
Maximilian Dreyer
Sebastian Lapuschkin
Wojciech Samek
AAML
124
1
0
28 Aug 2025
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
Maximilian Dreyer
Lorenz Hufe
J. Berend
Thomas Wiegand
Sebastian Lapuschkin
Wojciech Samek
196
2
0
26 May 2025
Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers
Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision TransformersTheory and Practice of Logic Programming (TPLP), 2025
Parth Padalkar
Gopal Gupta
137
0
0
10 May 2025
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
Sonia Joseph
Praneet Suresh
Lorenz Hufe
Edward Stevinson
Robert Graham
Yash Vadi
Danilo Bzdok
Sebastian Lapuschkin
Lee Sharkey
Blake A. Richards
403
8
0
28 Apr 2025
Interpreting the Second-Order Effects of Neurons in CLIP
Interpreting the Second-Order Effects of Neurons in CLIP
Yossi Gandelsman
Alexei A. Efros
Jacob Steinhardt
MILM
319
32
0
06 Jun 2024
Discriminative Class Tokens for Text-to-Image Diffusion Models
Discriminative Class Tokens for Text-to-Image Diffusion ModelsIEEE International Conference on Computer Vision (ICCV), 2023
Idan Schwartz
Vésteinn Snaebjarnarson
Hila Chefer
Robert Bamler
Serge Belongie
Lior Wolf
Sagie Benaim
310
12
0
30 Mar 2023
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional DivergenceInternational Conference on Learning Representations (ICLR), 2022
Frederik Pahde
Maximilian Dreyer
Leander Weber
Moritz Weckbecker
Christopher J. Anders
Thomas Wiegand
Wojciech Samek
Sebastian Lapuschkin
322
17
0
07 Feb 2022
1