Nora Belrose
5 papers · 2023–2025 · 3 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 ↓
๐
Conference Polyglot ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(10)
๐ฃ
Hot Topic Early Bird
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
representation learning
(1)
game playing
(1)
adversarial attack
(1)
linear classifier
(1)
recurrent neural network
(1)
language model
(1)
latent space
(1)
zero-shot transfer
(1)
sparse autoencoder
(1)
activation manipulation
(1)
concept erasure
(1)
bias reduction
(1)
interpretability method
(1)
embedding vector
(1)
model steering
(1)
transformer model
(1)
higher-order correlation
(1)
adversarial policies
(1)
agent vulnerability
(1)
activation addition
(1)
Papers
Automatically Interpreting Millions of Features in Large Language Models
ICML 2025
Do Transformer Interpretability Methods Transfer to RNNs?
AAAI 2025
Neural Networks Learn Statistics of Increasing Complexity
ICML 2024
Adversarial Policies Beat Superhuman Go AIs
ICML 2023
LEACE: Perfect linear concept erasure in closed form
NeurIPS 2023