© 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 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. 7676
    Prev
    Next
    INDEX
    Explanations

    information related to software development, specifically focusing on Python and Django programming

    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
    49
    +0.11
    0.5%
    106
    +0.10
    0.5%
    507
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.02
    632
    +0.10
    0.02
    66
    +0.10
    0.02
    Negative Logits
     showc
    -0.69
     redes
    -0.61
    è¦ļéĨĴ
    -0.61
    isure
    -0.61
    VERS
    -0.60
    ILY
    -0.59
     nause
    -0.59
     handy
    -0.59
    ãĥĥãĥī
    -0.59
     soak
    -0.59
    POSITIVE LOGITS
    unin
    0.74
     neither
    0.72
     which
    0.69
     however
    0.69
     nor
    0.67
     Nor
    0.67
    ulkan
    0.67
     wherein
    0.66
     whose
    0.64
     Shap
    0.62
    Activations Density 0.084%

    No Known Activations