© 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. 11820
    Prev
    Next
    INDEX
    Explanations

    names and titles of people

    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
    659
    +0.14
    0.7%
    481
    +0.12
    0.5%
    708
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.08
    232
    +0.12
    0.06
    406
    +0.10
    0.05
    Negative Logits
    perty
    -0.71
     Reincarn
    -0.70
     thous
    -0.69
    ÙIJ
    -0.65
    =-=-
    -0.62
     Thunderbolt
    -0.62
    catentry
    -0.61
     Leban
    -0.61
     SERV
    -0.61
    taboola
    -0.60
    POSITIVE LOGITS
    heed
    0.95
    gow
    0.85
    ibrary
    0.82
    ounge
    0.80
    oyd
    0.78
    udic
    0.77
    henko
    0.77
    emort
    0.76
    omez
    0.73
    ength
    0.72
    Activations Density 0.319%

    No Known Activations