Skip to content
Sagan

Paper

A Mechanistic Investigation of Supervised Fine Tuning

Unreadunread

AI summary

The author shows that while cosine similarity between pre- and post-SFT activations stays very high (suggesting little change), projecting both through a Sparse Autoencoder reveals that the underlying sparse features diverge significantly. Using SAEs as a diagnostic tool, they identify task-specific and layer-specific distributions of semantic features that are systematically altered during fine-tuning, and discover a layer-wise update profile specific to safety alignment.

Main takeaways:

  • High activation cosine similarity after SFT is misleading—the sparse latent structure changes substantially even when dense activations look similar.
  • Sparse Autoencoders pretrained on the base model can be used to measure which interpretable features are altered by fine-tuning.
  • The changes are task-specific and layer-specific: different fine-tuning objectives modify different semantic features in different layers.
  • Safety alignment shows a characteristic layer-wise update profile distinct from other fine-tuning tasks.
  • The method provides a high-resolution mechanistic view of what SFT actually changes beneath surface-level geometry.