© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 5858
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %
    -0.10
    .write
    -0.07
    _city
    -0.06
    .parent
    -0.06
    _distances
    -0.06
    +
    -0.06
    -
    -0.06
    _capacity
    -0.05
    _room
    -0.05
    |>
    -0.05
    POSITIVE LOGITS
    ))
    0.09
    join
    0.07
    rib
    0.06
    umn
    0.06
    ber
    0.06
    ulation
    0.05
    µ
    0.05
    ))<|
    0.05
    ion
    0.05
    atri
    0.05
    Activations Density 3.373%

    No Known Activations