Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer

Paper: Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer TL;DR: Maia-3 is a transformer-based chess model that takes Elo (the standard metric for competitive chess skill) as an input to the pre-trained network, so you can vary the skill the network is conditioned on with no change to its weights. Turning that Elo dial up from 700 to 2500: Pushes the computation deeper, monotonically, for every chess piece and move type I measured. This "depth migration" happens most for specific tactics, especially knight forks. The mechanism appears to consist of deeper (later) heads getting recruited for more specialized computations while shallow (earlier) heads keep a roughly constant contribution. 1. A falsifiable prediction One might predict that the migration would be to shallower layers as skill increased. In a neural network, the more layers there are after a feature is computed, the more opportunities there are to use that feature in subsequent computations. So a more advanced and skilled network should learn features like forks earlier on to reuse them in later layers. Tom Griffiths suggested this as one plausible prediction to me, and I found it convincing. The opposite occurs in this data. Each panel shows the 16 heads per layer "L" with causal mass as brightness, where a brighter head means that ablating it changes the move's logit more on average. Columns are Elo, orange line is center of mass. 2. The setup Maia-3 is a transformer-based ches…