Adam Karvonen

3 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICML (2) NeurIPS (1)

Top co-authors

Neel Nanda (2) Can Rager (2) Samuel Marks (2) Jannik Brinkmann (1) Curt Tigges (1) Rico Angell (1) Bart Bussmann (1) Johnny Lin (1) Yeu-Tong Lau (1) Eoin Farrell (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Core Methods (3) Deep Learning (2) Natural Language Processing (2) Architectures (2) Resources & Methods (2) Learning Types (1)

Keywords

sparse autoencoder (3) feature disentanglement (2) interpretability (1) language model (1) hierarchical feature (1) language model interpretability (1) ground truth metric (1) interpretable representation (1) large language model (1) board game (1) unlearning (1) concept reconstruction (1) dictionary size (1) nested dictionaries (1) dictionary learning (1) saebench (1) feature extraction (1)

Papers

Learning Multi-Level Features with Matryoshka Sparse Autoencoders ICML 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 NeurIPS 2024