Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Aaquib Syed
OpenAlex ID:
A5108853245
Refusal in Language Models Is Mediated by a Single Direction
2024
·
Andy Arditi
, Oscar Obeso
, et al.
·
neural information processing systems
·
71
Attribution Patching Outperforms Automated Circuit Discovery
2024
·
Aaquib Syed
, Can Rager
, et al.
·
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)
·
13
PDF
Show more works
View as search
Works count:
2
Citation count:
84
H-index:
2
I10-index:
2
Year
Topic
Type
