© 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. 22763
    Prev
    Next
    INDEX
    Explanations

    variations of the word "see."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    238
    +0.10
    0.5%
    373
    +0.10
    0.5%
    268
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.10
    0.01
    268
    +0.10
    0.01
    395
    +0.09
    0.01
    Negative Logits
     whistle
    -0.63
    raid
    -0.60
    cult
    -0.60
     hurd
    -0.57
     vocal
    -0.56
    naires
    -0.56
     Faust
    -0.56
     nerv
    -0.54
     conver
    -0.54
     stout
    -0.53
    POSITIVE LOGITS
    iful
    0.70
    iquette
    0.68
    Property
    0.63
    Privacy
    0.63
    Widget
    0.61
    lez
    0.61
    gments
    0.60
    iframe
    0.60
     Twice
    0.60
     whats
    0.60
    Activations Density 0.013%

    No Known Activations