World Modeling in Transformers
Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT, a transformer trained on random walks through Manhattan whose failures have been interpreted as evidence of an incoherent internal map. Through mechanistic analysis and causal interventions, we show that the model represents…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
