Alexandre Variengien

According to our database, Alexandre Variengien authored at least 6 papers between 2020 and 2024.

Collaborative distances:

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

2024

BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards.

Diego Dorn, Alexandre Variengien, Charbel-Raphaël Ségerie, Vincent Corruble

CoRR, 2024

2023

Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models.

Alexandre Variengien, Eric Winsor

CoRR, 2023

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model.

Michael Hanna, Ollie Liu, Alexandre Variengien

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small.

Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2021

Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent.

Alexandre Variengien, Stefano Nichele, Tom Eivind Glover, Sidney Pontes-Filho

CoRR, 2021

2020

A journey in ESN and LSTM visualisations on a language task.

Alexandre Variengien, Xavier Hinaut

CoRR, 2020