Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2502.10927
Cited By
v1
v2 (latest)
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
15 February 2025
Matteo Saponati
Pascal Sager
Pau Vilimelis Aceituno
Thilo Stadelmann
Benjamin Grewe
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training"
1 / 1 papers shown
Title
A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
Daking Rai
Yilun Zhou
Shi Feng
Abulhair Saparov
Ziyu Yao
187
33
0
02 Jul 2024
1