Structurally distinct circuits for literal sequence copying across token frequency bands implement the same computation, shown by broad transfer of band-specific edges, a shared core recovering 99% performance, and interchangeable representations via causal interventions.
arXiv preprint arXiv:2410.11985 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Markov chain Phase-Type decoders in VAEs enable heavy-tailed generation where Gaussian decoders fail due to structural limitations from Lipschitz continuity.
citing papers explorer
-
Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery
Structurally distinct circuits for literal sequence copying across token frequency bands implement the same computation, shown by broad transfer of band-specific edges, a shared core recovering 99% performance, and interchangeable representations via causal interventions.
-
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
Markov chain Phase-Type decoders in VAEs enable heavy-tailed generation where Gaussian decoders fail due to structural limitations from Lipschitz continuity.