© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11924
    Prev
    Next
    INDEX
    Explanations

    code snippets and specific programming terms

    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
    447
    +0.15
    0.7%
    718
    +0.13
    0.6%
    670
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.03
    314
    +0.13
    0.01
    659
    +0.11
    0.04
    Negative Logits
    naissance
    -0.74
     Flavoring
    -0.72
     bir
    -0.71
     Cumber
    -0.70
     jams
    -0.69
     bandwagon
    -0.68
     Circus
    -0.68
     Trou
    -0.65
    abouts
    -0.65
     Addiction
    -0.64
    POSITIVE LOGITS
    Measure
    0.87
    Input
    0.87
     =>
    0.85
    Print
    0.85
    Value
    0.85
    Frame
    0.83
    Integer
    0.82
    Default
    0.81
    Required
    0.81
    uler
    0.80
    Activations Density 0.104%

    No Known Activations