Adam Karvonen

According to our database, Adam Karvonen authored at least 13 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers.

Adam Karvonen, James Chua, Clément Dumas, Kit Fraser-Taliente, Subhash Kantamneni, Julian Minder, Euan Ong, Arnab Sen Sharma, Daniel Wen, Owain Evans, Samuel Marks

CoRR, December, 2025

DiFR: Inference Verification Despite Nondeterminism.

Adam Karvonen, Daniel Reuter, Roy Rinberg, Luke Marks, Adrià Garriga-Alonso, Keri Warr

CoRR, November, 2025

Verifying LLM Inference to Prevent Model Weight Exfiltration.

Roy Rinberg, Adam Karvonen, Alex Hoover, Daniel Reuter, Keri Warr

CoRR, November, 2025

Automatically Finding Rule-Based Neurons in OthelloGPT.

Aditya Singh, Zihang Wen, Srujananjali Medicherla, Adam Karvonen, Can Rager

CoRR, November, 2025

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning.

Helena Casademunt, Caden Juang, Adam Karvonen, Samuel Marks, Senthooran Rajamanoharan, Neel Nanda

CoRR, July, 2025

Robustly Improving LLM Fairness in Realistic Settings via Interpretability.

Adam Karvonen, Samuel Marks

CoRR, June, 2025

Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need.

Adam Karvonen

CoRR, March, 2025

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda

CoRR, March, 2025

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Isaac Bloom, David Chanin, Yeu-Tong Lau, Eoin Farrell, Callum McDougall, Kola Ayonrinde, Demian Till, Matthew Wearden, Arthur Conmy, Samuel Marks, Neel Nanda

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Learning Multi-Level Features with Matryoshka Sparse Autoencoders.

Bart Bussmann, Noa Nabeshima, Adam Karvonen, Neel Nanda

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks.

Adam Karvonen, Can Rager, Samuel Marks, Neel Nanda

CoRR, 2024

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models.

Adam Karvonen

CoRR, 2024

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models.

Adam Karvonen, Benjamin Wright, Can Rager, Rico Angell, Jannik Brinkmann, Logan Smith, Claudio Mayrink Verdun, David Bau, Samuel Marks

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024