Jack Merullo

Uncertainty in LLM reasoning is largely a sampling artifact, allowing for more efficient analyses that cut costs without sacrificing accuracy.

Sparse autoencoders, despite their popularity for extracting interpretable features, often fail to capture the underlying manifold structure of concepts, instead fragmenting them across multiple, diluted features.

LLMs often know the answer long before their "reasoning" suggests, wasting tokens on performative chain-of-thought.