© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 5554
    Prev
    Next
    INDEX
    Explanations

    text related to recipes and cooking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    509
    +0.13
    0.6%
    414
    +0.11
    0.5%
    730
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.13
    0.03
    665
    +0.11
    0.06
    608
    +0.11
    0.06
    Negative Logits
    itled
    -0.68
    reys
    -0.68
     whence
    -0.60
    URI
    -0.60
     unaccount
    -0.60
     bytes
    -0.60
     evidently
    -0.58
     Credits
    -0.58
     transcript
    -0.58
    usive
    -0.57
    POSITIVE LOGITS
     everyday
    1.03
     Everyday
    0.83
     salads
    0.80
     kitchens
    0.79
     shelf
    0.76
     classrooms
    0.72
    aspberry
    0.72
     fireplace
    0.71
     nurs
    0.69
     brunch
    0.68
    Activations Density 0.631%

    No Known Activations