# A Conditional No-Hair Theorem for Transformers: How Language Models Forget Their Prompt > Source: > Published: 2026-10-20 09:00:04+00:00 We ask how much an autoregressive transformer retains of its prompt after generating t tokens. Consider two different prompts followed by the same continuation text, so that any difference in their hidden states comes from the prompt alone, and we find that the distance between their hidden states d