© 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 12288
    9. 8-RES_FS12288-JB
    11. 10470
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Doug

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    339
    +0.14
    0.7%
    267
    +0.12
    0.5%
    659
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    232
    +0.12
    0.02
    81
    +0.12
    0.02
    Negative Logits
    itia
    -0.82
    istic
    -0.82
    */(
    -0.79
    culosis
    -0.71
    Interstitial
    -0.71
    200000
    -0.70
    istically
    -0.70
    istical
    -0.69
    itudes
    -0.69
    mberg
    -0.68
    POSITIVE LOGITS
    herty
    1.54
     Fir
    0.93
    ards
    0.89
    ermott
    0.87
     Hof
    0.86
    ARDS
    0.82
    aneers
    0.82
     Ell
    0.81
    ARD
    0.81
    arded
    0.77
    Activations Density 0.084%

    No Known Activations