Hidden vector, Thought vectorlatent state, internal state사람이 읽지 못하기 때문에 hidden이라고 함 The hidden state is computed based on the current input and the previous hidden state이 프로세스는 순차적이었고 병렬화를 방해 Some Intuition on Attention and the TransformerWhat's the big deal, intuition on query-key-value vectors, multiple heads, multiple layers, and more.https://eugeneyan.com/writing/attention/