AI Engram (Kwon et al., 2026) formalizes the four engram criteria of neuroscience as a constrained inverse problem in weight space and solves it closed-form: concept-specific memory traces become linear objects that can be extracted once and combined arithmetically. Appendix F states the Compositional Memory States Hypothesis: edited models live on"a commutative manifold where the integration of A and B reaches a consistent equilibrium regardless of the learning sequence."The evidence base is single and paired edits -- in materials terms, single-cycle tests, in which fatigue accumulation is structurally invisible. Whether the hypothesis holds under sequential load is exactly the"temporal dynamics"question the paper defers to future work. We run that test on the authors'own reference implementation, at their reported best edit strength (TOFU alpha=0.6, a choice favoring the linearity hypothesis), with pre-registered predictions, across three model charges (two vendors, two architecture families). Four findings replicate across all three: (1) zero-shot composition and sequential re-calibrated editing diverge by 61-71% of the edit magnitude; (2) cut order is not interchangeable, and the effect scales with concept overlap -- in one charge the order of cutting two Paris landmarks decides whether an uninvolved third concept survives; (3) the survivors'layer-input covariances -- the method's own sufficient statistics, read as strain gauges -- drift monotonically with every further cut, in every surviving concept, in every charge; (4) erased knowledge partially returns under subsequent unrelated cuts. Appendix F's commutative-manifold hypothesis is thereby falsified for sequential editing; the single-edit results of the original paper are untouched. For unlearning-as-compliance: erasure certified today does not certify the artifact after its next edit.
Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organization forms during training is unknown: prior work has characterized finished models, not the formation process. We track formation step by step: we train a Pythia-410M model from scratch (two trajectories, bf16 and fp32) and run attribution patching at every step, alongside probes for gradient norms, effective updates, weight norms, and first-order loss decomposition across 14 tasks in four cognitive domains. Three findings. First, the modular map is pre-carved: before any learning, the dominant task pair already overlaps at ~3.6x the attribution substrate (a task-independent baseline), and its layer-0 concentration is an architecture-level constant on this model family. Second, the partition locks in through two sharp jumps whose amplitudes do not track the learning-rate schedule (the second reaching 20.4 sigma quiet-window / 6.2 sigma global), accompanied by gradient-level relative deprivation--winners receive 2.25->2.73x the loser's gradient supply, 9.5-11.5 standard deviations below a random control--that does not propagate to updates or weights. Third, deviation from the substrate appears only in the domain being learned, consistent with the hypothesis that modularity tracks learning. We close by separating the feature-level account we can defend from the mechanistic questions we cannot, and we pre-register the scale-threshold hypothesis behind our ongoing 2.8B experiments.
We introduce CMP (Cognitive Memory Primitive), an architecture that represents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns entirely through local, gradient-free updates, with no backpropagation anywhere in the network. We use this architecture to test a specific hypothesis: that catastrophic forgetting, usually treated as a training-time defect to be patched with replay or regularization, is instead a structural consequence of how backpropagation assigns credit and that a learning rule that is local and sparse by construction should resist it without a patch. On a controlled domain-incremental protocol across 15 text domains, three-seed replicated, CMP's backward transfer is 15-19x better than a matched-size Transformer trained with online EWC, and the result survives a domain-order control (reported as a range, +0.24 to +0.44, rather than a single figure). We report this alongside a real, substantial accuracy gap versus the Transformer baseline, a null result on a recognized vision benchmark, and a diagnosed, unresolved failure attempting to combine this architecture with a separate mechanism that improves raw accuracy, disclosed because an honest negative result is more useful than an omitted one. The central claim is narrow and falsifiable: local, sparse, non-backpropagation learning measurably resists catastrophic forgetting better than backpropagation with its standard fix, under conditions we state precisely.
This work adds to the Kathleen trunk a second memory layer -- a"notebook": a fixed-key holographic (HRR) associative store with a learned local write gate, a self-gating raw read, and write-triggered forgetting -- 25K parameters that attach to the logits of any trunk.
Test-Time Memory Calibration (TTMC), a novel gradient-free analytic framework that introduces a transductive calibration mechanism that seamlessly fuses the second-order statistics of the unlabelled test stream into the accumulated long-term memory via a closed-form solution, allowing for real-time alignment with the test distribution.
Yuyang Han, Zi-Yu Li, Diwei Su et al.· Proceedings of the 32nd ACM...· 0 citations
The results suggest that the combination of sparse representations, local learning, and persistent memory is a promising direction for continual learning, while motivating further investigation into the respective roles of learning rules, representations, and architectural design in mitigating catastrophic forgetting.
Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lines, and cognitive maps. These claims often rely on linear probing and activation steering applied to a single model, yet both methods are highly sensitive to measurement choices. A reported parallel may therefore reflect the model, the measurement procedure, or both. We audit four representative neuroscience-inspired paradigms across 17 models from five families, spanning $0.6$B to $72$B parameters. Our main experiment examines the causal steerability of concept directions. With raw activation units and a fixed layer and coefficient, steerability appears to increase with model scale, resembling an emergent capability. However, this pattern is produced by an uncalibrated pipeline rather than by a claim established in the steering literature. The trend depends jointly on raw units, the readout metric, and the operating point; correcting any one of these removes it. With residual-norm-comparable interventions and held-out operating-point selection, concept steering remains significant at every scale, but shows no significant trend across the Qwen3 series, although the confidence interval does not rule out a moderate positive slope. The remaining results are mixed. A linear geographic world map is consistently decodable in every tested checkpoint up to $72$B. Number magnitude is strongly encoded, but whether individual neurons appear bell-shaped or monotonic depends on the selection criterion. Language-specific structure is localizable, but the direction of the cross-lingual asymmetry reverses under a different attribution method. These results suggest that the main constraint on AI neuroscience is not a lack of phenomena, but a lack of comparable measurements and adequate controls. We release the protocol, stimuli, and code.
Yuqi Wu, Shengming Zhao, Jie Chen· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
