transformer_lens.components.token_typed_embed

Hooked Transformer Token Typed Embed Component.

This module contains all the component TokenTypeEmbed.

class transformer_lens.components.token_typed_embed.TokenTypeEmbed(cfg: Dict | HookedTransformerConfig)

Bases: Module

The token-type embed is a binary ids indicating whether a token belongs to sequence A or B. For example, for two sentences: “[CLS] Sentence A [SEP] Sentence B [SEP]”, token_type_ids would be [0, 0, …, 0, 1, …, 1, 1]. 0 represents tokens from Sentence A, 1 from Sentence B. If not provided, BERT assumes a single sequence input. Typically, shape is (batch_size, sequence_length).

See the BERT paper for more information: https://arxiv.org/pdf/1810.04805.pdf

forward(token_type_ids: Int[Tensor, 'batch pos'])

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.