Get started
Author

Emmanuel Ameisen

Observed name: Ameisen, Emmanuel
Observed institution: Anthropic (United States)
OpenAlex ID: A5133647610
Auditing language models for hidden objectives
2025 · Marks, Samuel, Treutlein, Johannes, et al. · arXiv (Cornell University) · 4
PDF
Verbalizable Representations Form a Global Workspace in Language Models
2026 · Gurnee, Wes, Sofroniew, Nicholas, et al. · arXiv (Cornell University) · 1
PDF
Circuit-Tracer: A New Library for Finding Feature Circuits
2025 · Michael Hanna, Mateusz Piotrowski, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 1
PDF
Autonomous AI agents discover reverse transcriptases with tandem repeat arrays
2026 · Peter H. Yoon, Januka S. Athukoralage, et al. · bioRxiv (Cold Spring Harbor Laboratory)
A Shared Subcircuit Lets LLMs Count Down Across Tasks
2026 · Dunefsky, Jacob, Gurnee, Wes, et al. · arXiv (Cornell University)
PDF
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
2026 · Templeton, Adly, Conerly, Tom, et al. · arXiv (Cornell University)
PDF
Latent Planning Emerges with Scale
2026 · Hanna, Michael, Ameisen, Emmanuel · arXiv (Cornell University)
PDF
Mechanisms of Introspective Awareness
2026 · Macar, Uzay, Yang, Li, et al. · arXiv (Cornell University)
PDF
When Models Manipulate Manifolds: The Geometry of a Counting Task
2026 · Gurnee, Wes, Ameisen, Emmanuel, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count: 6
H-index: 1
I10-index:
Year
Topic
Type