conftrace_

Samuel Marks

4 papers · 2024–2025 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

+1 more ↓

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (8) 🐣 Hot Topic Early Bird

👥 Mega-Team (20)

Conferences

ICLR (2) ICML (1) NIPS (1)

Top co-authors

Can Rager (4) David Bau (3) Jannik Brinkmann (2) Adam Karvonen (2) Aaron Mueller (2) Neel Nanda (1) Curt Tigges (1) Eoin Farrell (1) Arnab Sen Sharma (1) Johnny Lin (1)

Keywords

dictionary learning (1) feature extraction (1) feature disentanglement (1) language model (1) sparse autoencoder (1) language model interpretability (1) ground truth metric (1) board game (1)

Papers

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals ICLR 2025 Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models ICLR 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NIPS 2024