Some observations about NLA explanations

I used the Gemma 3 12B activation verbalizer (maps activations to English) and reconstructor (maps English to activations) described in the Natural Language Autoencoders (NLA) paper to generate a bunch of explanations for 20k random tokens from a pretraining dataset (Common Pile derivative) and another 20k random tokens from a chat dataset. I also reconstructed all of the activations from the verbalizations so that I could see what kinds of tokens and explanations have high reconstruction error....