Skip to content
conftrace_

self-attention circuit

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) abstraction head (1) symbolic inference (1) symbolic abstraction (1) in-context learning (1) self-attention mechanism (1) representation learning (1)

Papers

Emergence of symbolic abstraction heads for in-context learning in large language models COLING 2025