# What is the number of neurons for the input layer of the BERT?

I think it is the vocab size. However I am not sure and I appreciate your help.

• About the "padding", it is used in NLP networks, but for the case when you group multiple sentences in the same mini-batch. In that case, the vocabulary contains a special <pad> token that is used to fill up the sentences that are shorted than the longest sentence. – noe Jan 7 at 11:36