OpenAI

Experts from OpenAI published a study in which they described how they tried to explain the work of neurons of its predecessor, GPT-2, using the GPT-4 language model.

Now the company's developers are trying to advance in the "interpretability" of neural networks and understand why they create the exact content we receive.

One explanation for this failure, suggested by OpenAI, is that neurons can be "polysemantic," meaning that a typical neuron in the context of a study can have multiple meanings or be associated with multiple concepts. In addition, language models can contain "alien concepts" for which people simply do not have words.