← Authors

Senthooran Rajamanoharan

4 papers · 2024–2025 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (4) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15) ❓ The Questioner (2)

Conferences

EMNLP (1) ICLR (1) ICML (1) NIPS (1)

Top co-authors

Neel Nanda (4) Arthur Conmy (2) JΓ‘nos KramΓ‘r (2) Rohin Shah (2) Tom Lieberum (2) Lewis Smith (2) Vikrant Varma (2) Oscar Balcells Obeso (1) Javier Ferrando (1) Max Tegmark (1)

Keywords

sparse autoencoder (2) neural network interpretability (1) model analysis (1) latent representation (1) language model (1) feature decomposition (1) interpretable feature (1) feature learning (1) activation decomposition (1)

Papers

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models ICLR 2025
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing ICML 2025
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders NIPS 2024
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 EMNLP 2024