© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7665
    Prev
    Next
    INDEX
    Explanations

    functions or procedures being passed as arguments in programming

    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
    683
    +0.12
    0.5%
    433
    +0.11
    0.5%
    178
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    326
    +0.11
    0.02
    683
    +0.10
    0.02
    Negative Logits
    hya
    -0.82
    achus
    -0.79
    aeda
    -0.77
    hai
    -0.77
    ¯
    -0.74
    alus
    -0.73
    xual
    -0.73
    yip
    -0.72
    gdala
    -0.71
    ynthesis
    -0.71
    POSITIVE LOGITS
    shots
    0.81
    ters
    0.75
    rative
    0.73
    ursed
    0.69
    imes
    0.68
    rating
    0.68
    office
    0.66
    shot
    0.65
    idious
    0.62
    sburgh
    0.62
    Activations Density 0.055%

    No Known Activations