paper:arxiv-2408-10920Recurrent neural networks learn to store and generate sequences using non-linear representations
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 79%
- ≈ 78%
- Neural networks leverage nominally quantum and post-quantum representationsPaul M. Riechers and Thomas J. Elliott and Adam S. Shai2025≈ 78%
- Discrete Latent Structure in Neural NetworksCaio F. Corro, Nikita Nangia, Tsvetomila Mihaylova, Andr\'e F. T. Martins Vlad Niculae2026≈ 78%
- ≈ 78%
- ≈ 78%
- Mechanistic Interpretability of RNNs emulating Hidden Markov ModelsMichele Viscione, Lucas Pompe, Benjamin F Grewe, Valerio Mante Elia Torre2025≈ 77%
- Dynamical similarity analysis can identify compositional dynamics developing in RNNsMicha{\l} W\'ojcik, Jascha Achterberg, Rui Ponte Costa Quentin Guilhot2024≈ 76%
- Lifelong Neural Predictive Coding: Learning Cumulatively Online without ForgettingAnkur Mali, Daniel Kifer, C. Lee Giles Alexander Ororbia2022≈ 76%
- A Cognitive Architecture for Machine Consciousness and Artificial Superintelligence: Thought Is Structured by the Iterative Updating of Working MemoryJared Edward Reser2024≈ 76%
- Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity AnalysisAdam Eisen, Leo Kozachkov, Ila Fiete Mitchell Ostrow2023≈ 76%
- Identifying Connectivity Distributions from Neural Dynamics Using FlowsUlises Pereira-Obilinovic, Yiliu Wang, Eric Shea-Brown, Uygar S\"umb\"ul Timothy Doyeon Kim2026≈ 76%
- Artificial Intelligence Software Structured to Simulate Human Working Memory, Mental Imagery, and Mental ContinuityJared Edward Reser2026≈ 75%
- On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World ModelsJuergen Schmidhuber2015≈ 75%
- ≈ 75%
- Learning without neurons in physical systemsin corpus2022≈ 74%
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?in corpus2025≈ 74%
- Relating transformers to models and neural representations of the hippocampal formationin corpus2021≈ 73%
- The Platonic Representation Hypothesisin corpus2024≈ 71%
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationsin corpus2023≈ 71%
- ≈ 71%
- Self-Improvising Memory: A Perspective on Memories as Agential, Dynamically Reinterpreting Cognitive Gluein corpus2024≈ 71%
- ≈ 70%
- ≈ 70%
- The World Inside Neural Networksin corpus2026≈ 70%
- ≈ 70%
- Model Alignment Searchin corpus2025≈ 69%
Similar preprints — Semantic Scholar
Cited by (4)
- Addressing divergent representations from causal interventions on neural networks
Causal intervention methods central to mechanistic interpretability—including activation patching, mean-difference vector patching, Sparse Autoencoders, and Distributed Alignment Search (DAS)—systemat
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
Under arbitrarily powerful alignment maps, causal abstraction becomes vacuous: any neural network can be perfectly mapped to any algorithm, a result proven formally in Theorem 1 under five mild assump
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering — intervening on model activations along paths constrained to lie on a learned activation manifold M_h rather than along Euclidean linear directions — produces behavioral trajectorie
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as