Transluce

To effectively oversee AI systems, we need to measure how they behave in the world, not just their capabilities. In a new essay, we describe our vision for an open scientific ecosystem for model behavior evaluation, and the public infrastructure required to support it.

Transluce is developing end-to-end interpretability approaches that directly train models to make predictions about AI behavior. Today we introduce Predictive Concept Decoders (PCD), a new architecture that embodies this approach.

New blog post out: a position piece on "Turning Compute into Understanding", by training superhuman oversight assistants.

Is your LM secretly an SAE? Most circuit-finding interpretability methods use learned features rather than raw activations, based on the belief that neurons do not cleanly decompose computation. In our new work, we show MLP neurons actually do support sparse, faithful circuits!