SVD on the lm_head weight matrix of transformers reveals interpretable vocabulary clusters that indicate training data composition, model differences, and ethical concerns in models like GPT-OSS, Gemma, and Qwen.
Backward lens: Projecting language model gradients into the vocabulary space
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.
citing papers explorer
-
Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
SVD on the lm_head weight matrix of transformers reveals interpretable vocabulary clusters that indicate training data composition, model differences, and ethical concerns in models like GPT-OSS, Gemma, and Qwen.
-
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.