© 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. 2687
    Prev
    Next
    INDEX
    Explanations

    statements of knowledge or fact

    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
    157
    +0.10
    0.5%
    750
    +0.10
    0.5%
    379
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.10
    0.03
    213
    +0.10
    0.03
    8
    +0.10
    0.03
    Negative Logits
    pex
    -0.99
    cohol
    -0.77
    ksh
    -0.77
    onies
    -0.76
    osi
    -0.75
    rentice
    -0.72
    onial
    -0.71
    inance
    -0.65
    paio
    -0.65
    ermanent
    -0.65
    POSITIVE LOGITS
     how
    0.95
     ourselves
    0.85
     anecd
    0.79
    ledged
    0.78
     instinctively
    0.74
     why
    0.71
     that
    0.71
    ledge
    0.71
     about
    0.69
     what
    0.69
    Activations Density 0.071%

    No Known Activations