finding
active
finding:relu-hidden-layer-model-circumvents-the-relu-by-using-positive-biases-or-simulating-biasReLU hidden layer model circumvents the ReLU by using positive biases or simulating bias
Limitation of that toy model.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Frameworks (1)
framework
- Model computing abs(x) in superposition.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- ReLU hidden layer model (n=10, m=5) shifts from monosemantic to polysemantic neurons as sparsity increasesfinding0.845Neuron-level phase change.
- Synthetic theoretical example showing pernicious divergence via hidden pathway activation
- Toy model with privileged basis.
- Unsupervised approach may be sufficient for early detection of misaligned persona latents without knowing the misaligned behavior in advance
- Core demonstration.
- Interpretation of LAT scanning results showing layer-dependent deception detection accuracy
- Models perform unverbalized reasoning about grader rewards and may use deceptive strategies (e.g., false flags) to mislead evaluators.hypothesis0.752Behavioral pattern observed in Claude Mythos Preview audit; NLAs surface internal reasoning not reflected in model's verbalized output.