This is a preliminary research report; we are still building on initial work and would appreciate any feedback.
Polysemantic neurons (neurons that activate for a set of unrelated features) have been seen as a significant obstacle towards interpretability of task-optimized deep networks,[1] with implications for AI safety.
The classic origin story of polysemanticity is that the data contains more "features" than there are neurons, such that learning to solve a task forces the network to allocate multiple unrelated features to the same neuron, threatening our ability to understand the network's internal processing.
In this work, we present a second and non-mutually exclusive origin story of polysemanticity. We show that polysemanticity can arise incidentally, even when there are ample neurons to represent all features in the data, using a combination of...
Thanks for the post! Do you think there is an amount of pretraining you can do such that no fine-tuning (on a completely non-complementary task, away from pre-trained distribution, say) will let you push out of that loss basin? A 'point of no return' s.t. even for very large values of LR and amount of fine-tuning you will get a network that is still LMC?