GPT-2

GPT-2 is a large language model used to evaluate the presence and influence of cognitive biases, such as anchoring bias, in its output distributions and decision-making processes.

Papers using GPT-2 (5)

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference2026Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum2026Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs2025Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization2025Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?2025