transformer_lens.model_bridge.supported_architectures.openai_gpt module

OpenAI GPT (GPT-1) architecture adapter.

The original GPT (OpenAIGPTLMHeadModel, openai-community/openai-gpt). GPT-2’s block internals under different top-level names — combined-QKV c_attn Conv1D, c_fc/c_proj MLP — but POST-norm (ln_1(x + attn), ln_2(n + mlp)), no final LayerNorm, and embeddings at transformer.tokens_embed / transformer.positions_embed.

class transformer_lens.model_bridge.supported_architectures.openai_gpt.OpenAIGPTArchitectureAdapter(cfg: Any)

Bases: ArchitectureAdapter

Architecture adapter for OpenAIGPTLMHeadModel (GPT-1) models.

__init__(cfg: Any) None

Initialize the OpenAI GPT architecture adapter.