# Figure request F3 toolkit: superderive language: cjk claim: 1/√d_k 是改写,不是新算子 grammar: derivation work_rel_dir: figures/F3 ## Flow stage: {name: D1, text: "缩放来自方差,不是装饰"} row: {name: R1} in_row: - {macro: sdstep, name: s1, role: rewrite, lhs: "QK^{\\top}", rhs: "QK^{\\top}/\\sqrt{d_k}"} - {macro: sdreason, name: s1, text: "§3.2.1,避免 softmax 饱和"}