Or Shafran

According to our database, Or Shafran authored at least 3 papers between 2025 and 2026.

Collaborative distances:

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

2026

From Directions to Regions: Decomposing Activations in Language Models via Local Geometry.

Or Shafran, Shaked Ronen, Omri Fahn, Shauli Ravfogel, Atticus Geiger, Mor Geva

CoRR, February, 2026

Constructing Interpretable Features from Compositional Neuron Groups.

Or David Shafran, Atticus Geiger, Mor Geva

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization.

Or Shafran, Atticus Geiger, Mor Geva

CoRR, June, 2025