Interpreting attention head outputs with NLAs

Natural language autoencoders are pretty interesting; I'm a big fan of using meta-models to interpret what's going on inside LLMs and NLAs seem like a promising route to understanding them better.One thing I've been interested in for a while is using NLAs to interpret the differences between activations: given an activation from an earlier and later layer, can we verbalize the changes between those two layers? It seems like it would be pretty cool if we could verbalize the activation diff betwee...