Alex Open Research Wiki

Tag: interpretability

8 items with this tag.

  • Jul 12, 2026

    Inference Dynamics

    • inference-dynamics
    • intermediate-layers
    • recurrent-depth
    • interpretability
  • Jun 20, 2026

    The Illusion of Superposition / Latent CoT Superposition Analysis

    • entity
    • latent-reasoning
    • superposition
    • interpretability
    • benchmark-hygiene
  • Jun 20, 2026

    The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models

    • latent-reasoning
    • superposition
    • interpretability
    • continuous-cot
    • training-dynamics
    • dynamic-compute
  • Jun 14, 2026

    Interpreting Atypical Conditions in Systems with Deep Conditional Autoencoders: The Case of Electrical Consumption

    • paper
    • power-systems
    • energy-demand
    • time-series
    • representation-learning
    • rare-events
    • interpretability
  • Jun 14, 2026

    Interpretable Policy Distillation for Power Grid Topology Control

    • paper
    • grid2op
    • power-systems
    • reinforcement-learning
    • policy-distillation
    • interpretability
    • control
  • May 29, 2026

    Dragon Hatchling

    • entity
    • sequence-models
    • state-space-models
    • fast-weights
    • recurrent-memory
    • interpretability
  • May 29, 2026

    The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain

    • sequence-models
    • state-space-models
    • fast-weights
    • recurrent-memory
    • interpretability
    • language-models
    • world-models
  • May 18, 2026

    Pre-trained Large Language Models Use Fourier Features To Compute Addition

    • number-tokenization
    • fourier-features
    • interpretability

Created with Quartz v4.5.2 © 2026