Self-attention b1 b3 ◆ 1 5 a2 Q1 Can be either input or a hidden layer 13Self-attention 𝒂 𝟒 𝒂 𝟑 𝒂 𝟐 𝒂 𝟏 𝒃 𝟒 𝒃 𝟑 𝒃 𝟐 𝒃 𝟏 Can be either input or a hidden layer 13