© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15318
    Prev
    Next
    INDEX
    Explanations

    questions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.21
    1.0%
    87
    +0.14
    0.6%
    108
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.21
    0.02
    85
    +0.14
    0.02
    464
    +0.10
    0.02
    Negative Logits
     manif
    -0.76
    wagen
    -0.69
     horizont
    -0.68
     toget
    -0.66
     Vaugh
    -0.65
     spont
    -0.64
     Swanson
    -0.63
     Gaw
    -0.63
     Dickinson
    -0.63
    schild
    -0.63
    POSITIVE LOGITS
    taboola
    1.02
    à¼
    0.87
     ][
    0.82
    Status
    0.79
     SHARES
    0.78
    actionDate
    0.78
    Product
    0.77
    Skip
    0.76
    ================================
    0.75
    Page
    0.73
    Activations Density 0.034%

    No Known Activations