Understand and debug your AI model
There is remarkable mathematical structure and geometry within neural networks. We help you uncover the hidden representations inside your model to remove the guesswork from AI training - going from alchemy to precision engineering.
We believe that AI is the most consequential technology of our time, yet today we train models with remarkably little understanding of the nature of their intelligence.
We’re the research lab dedicated to creating the science and technology to change that.
Silico is your interpretability agent
Explain, debug, and precisely control model behavior with state-of-the-art interpretability methods and infrastructure
Silico works across all types of AI models
Novel methods to understand,
debug, and design your AI model
Understand
Reverse engineer the causal mechanisms of AI to reveal its internal structure, uncovering novel science and validating when predictions reflect true understanding.
Neural networks have rich structure in their activations, underpinning their internal algorithms. We’ve developed new methods to map and edit this geometry, unlocking deeper interpretability and better control of model behavior.
We identified a novel class of biomarkers for Alzheimer's detection by interpreting an epigenetic model, the first major finding in the natural sciences obtained from reverse-engineering a foundation model.
We achieved state-of-the-art performance in predicting whether and how genetic variants cause disease, releasing interpretable-by-design predictions for all 4.2 million variants in the NIH’s ClinVar database.
Debug
Precisely debug issues with model behavior, identify and remove confounders, and diagnose failures before they occur in production.
Predictive data debugging lets us predict which behaviors RL on a preference dataset will amplify or suppress, trace that back to the responsible data, and reshape the data and/or training to prevent undesired effects.
Training often causes unexpected and undesired behaviors which show up only rarely, meaning evals often miss them. We can identify such behaviors by amplifying the diff between two checkpoints in logit space - a method now used for pre-deployment testing of frontier models.
We tracked “performative chain-of-thought”: when models “know” their final answer but continue to generate chain-of-thought anyways. We showed that probes can enable early exit from reasoning traces, saving up to 68% of tokens with minimal accuracy loss.
Design
Control training precisely to ensure your model learns what you want with less data and fewer off-target effects.
We cut hallucinations in an LLM by 58% by using interpretability to guide model training. Our approach was ~90x lower cost per intervention than LLM-as-judge, with no degradation in standard benchmarks.
We’re pioneering a new approach to interpretability which breaks down the actual weights, rather than the activations, of a model. The resulting components reveal the model’s computational structure and let us make targeted edits.
Our essay on intentional design describes our vision for using interpretability to guide model training – moving from guess-and-check to closed loop control.
Start researching with Silico
Download Silico for macOS, or talk with us about bringing it to your team and infrastructure.
