Alexander Matt Turner

According to our database, Alexander Matt Turner authored at least 12 papers between 2019 and 2024.

Collaborative distances:

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

2024

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks.

Alex Cloud, Jacob Goldman-Wetzler, Evzen Wybitul, Joseph Miller, Alexander Matt Turner

CoRR, 2024

Steering Llama 2 via Contrastive Activation Addition.

Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

Understanding and Controlling a Maze-Solving Policy Network.

Ulisse Mini, Peli Grietzer, Mrinank Sharma, Austin Meek, Monte MacDiarmid, Alexander Matt Turner

CoRR, 2023

Activation Addition: Steering Language Models Without Optimization.

Alexander Matt Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, Monte MacDiarmid

CoRR, 2023

2022

On Avoiding Power-Seeking by Artificial Intelligence.

Alexander Matt Turner

CoRR, 2022

Formalizing the Problem of Side Effect Regularization.

Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli

CoRR, 2022

Parametrically Retargetable Decision-Makers Tend To Seek Power.

Alexander Matt Turner, Prasad Tadepalli

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Optimal Policies Tend To Seek Power.

Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Avoiding Side Effects in Complex Environments.

Alexander Matt Turner, Neale Ratzlaff, Prasad Tadepalli

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Conservative Agency via Attainable Utility Preservation.

Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli

Proceedings of the AIES '20: AAAI/ACM Conference on AI, 2020

2019

Optimal Farsighted Agents Tend to Seek Power.

Alexander Matt Turner

CoRR, 2019

Conservative Agency.

Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli

Proceedings of the Workshop on Artificial Intelligence Safety 2019 co-located with the 28th International Joint Conference on Artificial Intelligence, 2019