Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired inductive biases, it is paramount to be able to explore what the attention has learned. While static analyses of these models lead to targeted insights, interactive tools are more dynamic and can help humans better gain an intuition for the model-internal reasoning process.

We present exBERT , an interactive tool named after the popular BERT language model, that provides insights into the meaning of the contextual representations by matching a human-specified input to similar contexts in a large annotated dataset. By aggregating the annotations of the matching similar contexts, exBERT helps intuitively explain what each attention-head has learned.

Thanks to Jesse Vig for feedback. Please let us know what you think by commenting below!

Tool screenshot

We collect information about your activity. Since we care about your privacy, all these information are fully anonymized. Check the links below for more information.


IBM Research, Cambridge
MIT-IBM Watson AI Lab