Eric J. Michaud
Scholar

Eric J. Michaud

Google Scholar ID: X52GetkAAAAJ
Graduate student, MIT
Deep LearningMechanistic Interpretability
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,819
 
H-index
12
 
i10-index
13
 
Publications
20
 
Co-authors
12
list available
Contact
No contact links provided.
Publications
8 items
There Will Be a Scientific Theory of Deep Learning
2026
Cited
0
Understanding sparse autoencoder scaling in the presence of feature manifolds
2025
Cited
0
On the creation of narrow AI: hierarchy and nonlocality of neural network skills
2025
Cited
0
Open Problems in Mechanistic Interpretability
2025
Cited
0
Physics of Skill Learning
2025
Cited
0
Efficient Dictionary Learning with Switch Sparse Autoencoders
arXiv.org · 2024
Cited
12
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Entropy · 2024
Cited
4
Not All Language Model Features Are One-Dimensionally Linear
2024
Cited
40
Resume (English only)
Co-authors
12 total
Max Tegmark
Max Tegmark
Professor of Physics, MIT
Ziming Liu
Ziming Liu
MIT
Joshua Engels
Joshua Engels
Google Deepmind
Yonatan Belinkov
Yonatan Belinkov
Technion
David Bau
David Bau
Assistant Professor at Northeastern University
Aaron Mueller
Aaron Mueller
Boston University
Co-author 7
Co-author 7
Co-author 8
Co-author 8