Conor Houghton
4 papers · 2019–2025 · 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
๐
Academic Marathon ยท Sprint
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Top co-authors
Research topics
Keywords
neural network
(2)
few-shot learning
(1)
information bottleneck
(1)
interpretability
(1)
mutual information
(1)
language model
(1)
activation function
(1)
latent activation
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
residual stream
(1)
representation compression
(1)
word embedding
(1)
grammatical gender
(1)
large language model
(1)
computational sparsity
(1)
jacobian sparse autoencoders
(1)
representation learning
(1)
sparsify computations
(1)
Papers
Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
ICML 2025
Residual Stream Analysis with Multi-Layer SAEs
ICLR 2025
Investigating grammatical abstraction in language models using few-shot learning of novel noun gender
EACL 2024
Adaptive Estimators Show Information Compression in Deep Neural Networks
ICLR 2019