Luke Marks
3 papers
· 2024–2025
· 2 conferences
· across top CS/AI conferences
Achievements
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(2)
🐝
Cross-Pollinator
(6)
📈
Trend Setter
Conferences
EMNLP (2)
NIPS (1)
Top co-authors
Keywords
neural network interpretability
(1)
reinforcement learning from human feedback
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
activation probe
(1)
learned feedback pattern
(1)
alignment verification
(1)
hidden state analysis
(1)
neural interpretability
(1)
multi-attribute control
(1)
text-to-sql generation
(1)
probing classifier
(1)
large language model
(1)
hidden activation
(1)
activation analysis
(1)
activation probing
(1)
linear steering
(1)
behavioral steering
(1)
gradient intervention
(1)
activation classifier
(1)