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

    Neuronpedia

    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. 4137
    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
    ility
    -0.06
    ithm
    -0.06
    ilities
    -0.06
    reshold
    -0.05
    ution
    -0.05
    mbol
    -0.05
    ighbour
    -0.05
    straint
    -0.05
    apping
    -0.05
    rror
    -0.05
    POSITIVE LOGITS
    ñ
    0.11
     "__
    0.11
    Ě
    0.11
     Define
    0.11
    Ú
    0.10
    Ę
    0.10
    Ĉ
    0.10
    Ô
    0.10
     '__
    0.09
    Ą
    0.09
    Activations Density 14.288%

    No Known Activations