© 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. 14838
    Prev
    Next
    INDEX
    Explanations

    ages such as youth categories in sports and specific numerical references related to sports events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    738
    +0.09
    0.4%
    247
    +0.09
    0.4%
    159
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    758
    +0.09
    0.01
    115
    +0.09
    0.02
    153
    +0.09
    0.01
    Negative Logits
     Berman
    -0.75
    paralle
    -0.75
     downstream
    -0.70
    onite
    -0.69
     upstream
    -0.67
     Medina
    -0.66
     nozzle
    -0.65
    odon
    -0.64
    oit
    -0.64
    ifully
    -0.64
    POSITIVE LOGITS
     basketball
    0.83
    uates
    0.81
     Athletic
    0.81
     rugby
    0.80
     football
    0.80
     cricket
    0.79
     athletics
    0.78
    s
    0.78
     Rugby
    0.78
     Football
    0.76
    Activations Density 0.053%

    No Known Activations