Autoencoder

Neural network architecture that learns compressed representations; SOHMs are functionally equivalent.

Neighborhood — ranked by edge-count

concept

Self-Organized Harmonic Modes (SOHMs)
associated_with
Adam Safron's framework for neural building blocks functioning as symmetry detectors/autoencoders; tanha-free awareness theorized as direct feeling of undoctored SOHMs.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Deep Autoencoderframework0.908
Deep Auto Encoderframework0.881
Sparse Autoencoderframework0.877
Interpretability framework used to decompose layer-40 activations into sparse feature sets for studying emotional alignment and persistence
Unsupervised autoencoder embeddingsmethod0.843
Method used alongside covariance pooling for the Gene Ontology prediction task; produces embeddings without large labeled datasets.
Masked Autoencodersconcept0.838
Self-supervised learning method that optimizes reconstruction tasks; included in the paper's analysis as a multi-task objective
Sparse Autoencoder Featuresconcept0.832
Used in Anthropic welfare assessment to identify performative behavior and hidden emotional struggle co-activating features
Natural Language Autoencoders (NLAs)method0.824
Core unsupervised method for generating natural language explanations of LLM activations through a verbalizer-reconstructor pair trained with RL.
Autoencoder Architecture (Variational)framework0.817
A machine-learning analogy: evolution learns both an encoding (genome compression) and a decoder (morphogenetic process); explains how evolution avoids overfitting and evolves general-purpose problem-solving.