/var/logmarcus chiu

/var/log

❯

Computer

❯

Artificial Intelligence (AI) - Cognitive Computing - Machine Intelligence

❯

AI - Subfields

❯

Machine Learning (ML) - Pattern Recognition

❯

ML - Models

❯

Artificial Neural Networks (ANN)

❯

ANN - Architectures

❯

Autoencoders (AE)

Sparse Autoencoders (SAE)

Created on Aug 18, 2020 · Last Modified on May 13, 2026

Sparse Autoencoders (SAE)
  • is a type of neural network used for unsupervised feature learning and dimensionality reduction
  • it is a variant of a standard autoencoder, but with an added sparsity constraint on the hidden layer activations

Use Cases

  • can be used for LLM Interpretability to see what’s going on within a neural network

Resources

  • https://web.stanford.edu/class/cs294a/sparseAutoencoder_2011new.pdf