Explainability

Overview

The Explainability module provides token attribution analysis to understand which parts of the input influence model outputs. It uses the interpreto library for token-level attribution.

Use case

Explainability helps you understand:

Which tokens in the input have the most influence on the output
Whether the model is attending to the right parts of the context
Potential biases in token-level attention patterns

Usage

from gaussia.explainability import TokenAttribution

attribution = TokenAttribution(
    model_name="bert-base-uncased",
)

results = attribution.analyze(
    text="The weather in Paris is sunny today.",
    target="sunny",
)

for token, score in results.attributions:
    print(f"{token}: {score:.4f}")

Requires the explainability extra: pip install "gaussia[explainability]".

Prompt optimizer

Getting started

Core concepts

Metrics

Integrations

Advanced

Overview

Use case

Usage

​Overview

​Use case

​Usage

Overview

Use case

Usage