conftrace_

Lee Sharkey

4 papers · 2024–2025 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15)

Conferences

ICLR (3) NIPS (1)

Top co-authors

Michael T Pearce (2) Curt Tigges (1) Neel Nanda (1) Hoagy Cunningham (1) Noura Al Moubayed (1) Jose Oramas (1) Bart Bussmann (1) Thomas Dooms (1) Logan Riggs Smith (1) Nicholas Goldowsky-Dill (1)

Keywords

feature extraction (1) neural network activation (1) mechanistic interpretability (1) sparse autoencoder (1) sparse dictionary learning (1)

Papers

Bilinear MLPs enable weight-based mechanistic interpretability ICLR 2025 Sparse Autoencoders Do Not Find Canonical Units of Analysis ICLR 2025 Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning NIPS 2024 Sparse Autoencoders Find Highly Interpretable Features in Language Models ICLR 2024