Language Models Have Interpretable Narrative Mechanisms
We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narrative properties. Across GPT-2-Small, Gemma-2-2B, and Llama-3.1-8B, we identify attention heads, MLP neurons, and sparse autoencoder features whose activations correlat...
David Liu, A. Joshi, Paul Dawson et al.
· 0 citations