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. 2502.12179
  4. Cited By
Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts

Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts

14 February 2025
Shruti Joshi
Andrea Dittadi
Sébastien Lachapelle
Dhanya Sridhar
    LLMSV
ArXiv (abs)PDFHTML

Papers citing "Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts"

1 / 1 papers shown
Title
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
Dong Shu
Xuansheng Wu
Haiyan Zhao
Jundong Li
Ninghao Liu
LLMSV
100
1
0
12 May 2025
1