principles.fyi · the brain · concept

logit lens

Peek at the model's running guess at every step, not just the end.

guess(layer) = read_words(scratchpad at that layer)

The model builds its answer in a tall stack of layers, each one nudging an internal scratchpad of numbers a little further along. The logit lens takes that scratchpad at every layer and runs it through the model's final word-reader early, asking "if you had to answer right now, what word?" Low down the guess is a fuzzy, common word; higher up it snaps into the real answer. It matters because it lets us watch a thought form, layer by layer, instead of only seeing the finished sentence.