Cite
Notes
Only stored in your browser.
Attribution
Activation Space Interventions Can Be Transferred Between Large Language Models
arXiv 2025
Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
arXiv 2024
from 2 papers
Abir Harrasse
Amirali Abdullah
Ashkan Khakzar
Austin Meek
David Krueger
Dhruv Nathawani
Fazl Barez
Narmeen Oozeer
Nirmalendu Prakash
Philip Torr