SAE latent vectors are not independent, but rather form clusters that activate together in predictable ways. While functionally separate, there are actual dependencies, making interactions and compositional characteristics important for interpretability. This is particularly evident in smaller SAEs, and these clusters can be effectively analyzed through L0 regularization.
SAE Latent Cooccurrence Explorer ()
sae_cooccurrence
MClarke1991 • Updated 2025 Jan 8 20:41
When two features frequently activate at the same time, we say they co-occur (high correlation)
Topological data analysis
Graph Modeling of SAE features displayed Relationship relevant features developing along the layers and latter layers involves more complex features.
