Words that strongly activate both a lower-layer neuron and its strongly connected upper-layer neuron in GPT-2XL form more semantically similar clusters, which the paper interprets as a clipping process.
Evaluating Neuron Interpretation Methods of NLP Models
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Neuron Interpretation has gained traction in the field of interpretability, and have provided fine-grained insights into what a model learns and how language knowledge is distributed amongst its different components. However, the lack of evaluation benchmark and metrics have led to siloed progress within these various methods, with very little work comparing them and highlighting their strengths and weaknesses. The reason for this discrepancy is the difficulty of creating ground truth datasets, for example, many neurons within a given model may learn the same phenomena, and hence there may not be one correct answer. Moreover, a learned phenomenon may spread across several neurons that work together -- surfacing these to create a gold standard challenging. In this work, we propose an evaluation framework that measures the compatibility of a neuron analysis method with other methods. We hypothesize that the more compatible a method is with the majority of the methods, the more confident one can be about its performance. We systematically evaluate our proposed framework and present a comparative analysis of a large set of neuron interpretation methods. We make the evaluation framework available to the community. It enables the evaluation of any new method using 20 concepts and across three pre-trained models.The code is released at https://github.com/fdalvi/neuron-comparative-analysis
citation-role summary
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition
Words that strongly activate both a lower-layer neuron and its strongly connected upper-layer neuron in GPT-2XL form more semantically similar clusters, which the paper interprets as a clipping process.