© 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. 16855
    Prev
    Next
    INDEX
    Explanations

    double-digit numerical values in a document

    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
    152
    +0.13
    0.6%
    537
    +0.12
    0.6%
    298
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.03
    152
    +0.12
    0.03
    366
    +0.09
    0.02
    Negative Logits
     Lauder
    -0.64
     TODAY
    -0.64
     EntityItem
    -0.64
     Wanted
    -0.64
     companion
    -0.63
    ################################
    -0.62
     Sikh
    -0.61
     Zar
    -0.60
     Guru
    -0.60
    ðŁĺ
    -0.60
    POSITIVE LOGITS
    digit
    1.20
    edged
    1.16
    sided
    1.03
    sized
    1.02
    handed
    1.00
    faced
    0.98
    headed
    0.98
    handedly
    0.95
    double
    0.93
    figure
    0.92
    Activations Density 0.022%

    No Known Activations