Synthetic Categorical Restructuring large Or How AIs Gradually Extract Efficient Regularities from Their Experience of the World
Not on the map. Why?
Abstract (arXiv)
How do language models segment their internal experience of the world of words to progressively learn to interact with it more efficiently? This study in the neuropsychology of artificial intelligence investigates the phenomenon of synthetic categorical restructuring, a process through which each successive perceptron neural layer abstracts and combines relevant categorical sub-dimensions from the thought categories of its previous layer. This process shapes new, even more efficient categories for analyzing and processing the synthetic system's own experience of the linguistic external world to which it is exposed. Our genetic neuron viewer, associated with this study, allows visualization of the synthetic categorical restructuring phenomenon occurring during the transition from perceptron layer 0 to 1 in GPT2-XL.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 98 references that are in the map. First posted on arXiv 25 Feb 2025.
Builds on
17 of 98 references.
References · 17
- 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
- 2021Knowledge Neurons in Pretrained Transformerscited by 590
- 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
- 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
- 2020Generating Fact Checking Explanationscited by 132
- 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
- 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
- 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
- 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
- 2022On the Transformation of Latent Space in Fine-Tuned NLP Modelscited by 19
- 2023Can LLMs facilitate interpretation of pre-trained language models?cited by 15
- 2024From Cognition to Computation: A Comparative Review of Human Attention and Transformer Architecturescited by 6
5 more
- 2024Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networkscited by 5
- 2023Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for Automated Structural Condition Assessment in Visual Inspectioncited by 4
- 2024Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognitioncited by 3
- 2024How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neuronscited by 3
- 2025The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognitioncited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.