The x-axis ($j$) is the end point of the duplicated region. The y-axis ($i$) is the start point. Each pixel represents a complete evaluation: load the re-layered model, run the math probe, run the EQ probe, score both, record the deltas. As described above, along the central diagonal only a single layer was duplicated. Along the next diagonal towards the top-right, we duplicate two layers, and so on. The single point at the very top-right runs through the entire Transformer stack twice per inference.
Dave Woolley and Kim Mast wrote a lesson called "=notes=". The =notes= lesson
，详情可参考safew
不过持续不断的投入终于让量变产生了质变。。谷歌对此有专业解读
NXT communications protocol