Samuel Marks

According to our database, Samuel Marks authored at least 5 papers between 2023 and 2024.

Collaborative distances:

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

2024

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data.

Johannes Treutlein, Dami Choi, Jan Betley, Cem Anil, Samuel Marks, Roger Baker Grosse, Owain Evans

CoRR, 2024

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Carson Denison, Monte MacDiarmid, Fazl Barez, David Duvenaud, Shauna Kravec, Samuel Marks, Nicholas Schiefer, Ryan Soklaski, Alex Tamkin, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Ethan Perez, Evan Hubinger

CoRR, 2024

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller

CoRR, 2024

2023

The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Samuel Marks, Max Tegmark

CoRR, 2023

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Stephen Casper, Xander Davies, Claudia Shi, Thomas Krendl Gilbert, Jérémy Scheurer, Javier Rando, Rachel Freedman, Tomasz Korbak, David Lindner, Pedro Freire, Tony Wang, Samuel Marks, Charbel-Raphaël Ségerie, Micah Carroll, Andi Peng, Phillip J. K. Christoffersen, Mehul Damani, Stewart Slocum, Usman Anwar, Anand Siththaranjan, Max Nadeau, Eric J. Michaud, Jacob Pfau, Dmitrii Krasheninnikov, Xin Chen, Lauro Langosco, Peter Hase, Erdem Biyik, Anca D. Dragan, David Krueger, Dorsa Sadigh, Dylan Hadfield-Menell

CoRR, 2023