Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2409.17113
Cited By
Characterizing stable regions in the residual stream of LLMs
25 September 2024
Jett Janiak
Jacek Karwowski
Chatrik Singh Mangat
Giorgi Giglemiani
Nora Petrova
Stefan Heimersheim
Re-assign community
ArXiv
PDF
HTML
Papers citing
"Characterizing stable regions in the residual stream of LLMs"
2 / 2 papers shown
Title
Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
Daniel J. Lee
Stefan Heimersheim
AAML
24
4
0
16 Oct 2024
Evaluating Synthetic Activations composed of SAE Latents in GPT-2
Giorgi Giglemiani
Nora Petrova
Chatrik Singh Mangat
Jett Janiak
Stefan Heimersheim
LLMSV
30
3
0
23 Sep 2024
1