# Codeblock 8 Output
features & residual  : torch.Size([1, 576, 768])  #(1)
after self attention : torch.Size([1, 576, 768])
self attn weights    : torch.Size([1, 576, 576])  #(2)
after norm           : torch.Size([1, 576, 768])

features & residual  : torch.Size([1, 576, 768])
after ffn            : torch.Size([1, 576, 768])  #(3)
after norm           : torch.Size([1, 576, 768])  #(4)