© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4005
    Prev
    Next
    INDEX
    Explanations

    terms related to offensive performance in sports

    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
    278
    +0.10
    0.5%
    505
    +0.10
    0.4%
    379
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.10
    0.02
    505
    +0.10
    0.02
    379
    +0.10
    0.02
    Negative Logits
     Solitaire
    -0.94
    Deal
    -0.81
    bourg
    -0.79
    hyde
    -0.76
    etsk
    -0.75
    chell
    -0.75
    20439
    -0.73
    arnaev
    -0.72
    ilk
    -0.72
    bush
    -0.72
    POSITIVE LOGITS
     linemen
    1.17
     lineman
    1.10
     firepower
    0.81
     coordinator
    0.79
     offensive
    0.77
     tackle
    0.76
     rebounds
    0.76
     powerhouse
    0.75
     prowess
    0.75
     endeavour
    0.74
    Activations Density 0.013%

    No Known Activations