Nice work! I'm especially impressed by the [word] and [word] example: This cannot be read-off the embeddings, thus the model must be actually computing and storing this feature somewhere! I think this is exciting since the things we care about (deception etc.) are also definitely not included in the embeddings. I think you could make a similar case for Title Case and Beginning & End of First Sentence but those examples look less clear, e.g. the Title Case could be mostly stored in "embedding of uppercase word that is usually lowercase".
Thank you for making the early write-up! I'm not entirely certain I completely understand what you're doing, could I give you my understanding and ask you to fill the gaps / correct me if you have the time? No worries if not, I realize this is a quick & early write-up!
As previously you run Pythia on a bunch of data (is this the same data for all of your examples?) and save its activations.Then you take the residual stream activations (from which layer?) and train an autoencoder (like Lee, Dan & beren here) with a single hidden layer (w/ ReLU)
Hi, and thanks for the comment!
Do you think there should be a preference to the whether one patches clean --> corrupt or corrupt --> clean?
Both of these show slightly different things. Imagine an "AND circuit" where the result is only correct if two attention heads are clean. If you patch clean->corrupt (inserting a clean attention head activation into a corrupt prompt) you will not find this; but you do if you patch corrupt->clean. However the opposite applies for a kind of "OR circuit". I historically had more success with corrupt->clean s... (read more)
Thank for for the extensive comment! Your summary is really helpful to see how this came across, here's my take on a couple of these points:
2.b: The network would be sneaking information about the size of the residual stream past LayerNorm. So the network wants to implement an sort of "grow by a factor X every layer" and wants to prevent LayerNorm from resetting its progress.