Gustaw Opielka

According to our database, Gustaw Opielka authored at least 5 papers between 2024 and 2026.

Collaborative distances:

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

2026

Causality ≠ Invariance: Function and Concept Vectors in LLMs.

Gustaw Opielka, Hannes Rosenbusch, Claire E. Stevenson

CoRR, February, 2026

2025

Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction.

Gustaw Opielka, Hannes Rosenbusch, Claire E. Stevenson

CoRR, March, 2025

Cognitively Inspired Interpretability in Large Neural Networks.

Anna Leshinskaya, Taylor W. Webb, Ellie Pavlick, Jiahai Feng, Gustaw Opielka, Claire E. Stevenson, Idan A. Blank

Proceedings of the 47th Annual Meeting of the Cognitive Science Society, 2025

2024

Saliency Suppressed, Semantics Surfaced: Visual Transformations in Neural Networks and the Brain.

Gustaw Opielka, Jessica Loke, H. Steven Scholte

CoRR, 2024

Do large language models solve ARC visual analogies like people do?

Gustaw Opielka, Hannes Rosenbusch, Veerle Vijverberg, Claire E. Stevenson

Proceedings of the 46th Annual Meeting of the Cognitive Science Society, 2024