A Structural Interpretation of GELU and Threshold-Transmission Activations via the First-Order Loss Function

arXiv:2607.03664 · cs.LG, math.OC, stat.ML · Submitted 2026-07-04 · Read on arXiv

Roberto Rossi

cs.LG, math.OC, stat.ML

Submitted: 2026-07-04

Comments: 18 pages, 8 figures, 8 tables

Code: https://github.com/karpathy/char-rnn

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 14× in this paper · explained in 2 episodes
• Perplexity — 12× in this paper · explained in 3 episodes
• Loss Function — 11× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Editor — 5× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Decoder — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Weight Decay — 3× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Overfitting — 1× in this paper · explained in 2 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformers — 1× in this paper · explained in 2 episodes

Sources

• TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
• Gaussian Error Linear Units (GELUs)
• Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks