© 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. 2973
    Prev
    Next
    INDEX
    Explanations

    legal and political terms and agreements

    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
    481
    +0.21
    1.0%
    447
    +0.18
    0.9%
    440
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.21
    0.04
    632
    +0.18
    0.04
    440
    +0.11
    0.04
    Negative Logits
    swick
    -0.72
    wow
    -0.71
    inventoryQuantity
    -0.69
    Morning
    -0.67
    Untitled
    -0.67
    Wow
    -0.65
    rir
    -0.63
    grim
    -0.63
    Jere
    -0.62
    sie
    -0.61
    POSITIVE LOGITS
     whenever
    0.94
     users
    0.81
     payments
    0.76
     unless
    0.76
    users
    0.76
     Users
    0.75
     allowable
    0.75
     refunds
    0.75
     electors
    0.74
     applicants
    0.74
    Activations Density 0.332%

    No Known Activations