© 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. 16285
    Prev
    Next
    INDEX
    Explanations

    measurements and units of time

    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
    678
    +0.14
    0.7%
    67
    +0.12
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.05
    238
    +0.12
    0.05
    67
    +0.11
    0.05
    Negative Logits
    worldly
    -0.94
    artisan
    -0.67
    kok
    -0.67
    estate
    -0.67
    heastern
    -0.62
    lightly
    -0.62
    polit
    -0.61
    alter
    -0.61
    atically
    -0.61
    istically
    -0.60
    POSITIVE LOGITS
     intervals
    0.87
     consecut
    0.85
     increments
    0.83
    +,
    0.82
    +.
    0.79
     onwards
    0.77
     hindsight
    0.76
    +)
    0.76
     Anniversary
    0.72
     consecutive
    0.70
    Activations Density 0.176%

    No Known Activations