Wes Gurnee
4 papers · 2024–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
representation learning
(1)
feature extraction
(1)
model interpretability
(1)
spatial representation
(1)
world model
(1)
sparse autoencoder
(1)
token frequency
(1)
safety fine-tuning
(1)
modular arithmetic
(1)
residual stream
(1)
linear representation
(1)
temporal representation
(1)
layer normalization
(1)
entity encoding
(1)
logit scaling
(1)
large language model
(1)
weight editing
(1)
entropy neuron
(1)
refusal direction
(1)
circular feature
(1)