concept
active
concept:pre-encoder-bias

Pre-Encoder Bias

Architectural modification subtracting a learned bias from autoencoder inputs before encoding; initialized to geometric median of dataset; improves autoencoder performance

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Related by similarity (8)

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.

  • Features related to gender, racial, ethnic biases, slurs, and hate speech.
  • Inductive Biasconcept0.748
    Assumptions or preferences (e.g., parsimony) that determine how a learning system generalizes beyond training data
  • Bias Amplificationconcept0.747
    Problem cited as a limitation of current LLMs; PRH predicts larger models should amplify bias less
  • Autoencoderconcept0.742
    Neural network architecture that learns compressed representations; SOHMs are functionally equivalent.
  • Deep Auto Encoderframework0.739
  • Encoders read pre-MLP space; decoders reconstruct pre-MLP and MLP output to find newly computed features.
  • Train a single SAE encoding and decoding activations from two models simultaneously to find shared and exclusive features.
  • Expected prevalence of patterns (e.g., base-10 arithmetic) in pretraining corpora, influencing ρd and dr.