© 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. 4019
    Prev
    Next
    INDEX
    Explanations

    words related to specific countries and political activities

    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
    311
    +0.11
    0.5%
    346
    +0.10
    0.5%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.01
    28
    +0.10
    0.01
    107
    +0.10
    0.01
    Negative Logits
     disenfranch
    -0.76
     Royale
    -0.62
     vulner
    -0.62
    etsk
    -0.60
    pton
    -0.60
    Downloadha
    -0.59
     impart
    -0.59
    afort
    -0.57
    arette
    -0.57
     delinqu
    -0.57
    POSITIVE LOGITS
    Ĺ
    1.05
    ¤
    0.91
    OWN
    0.85
    ķ
    0.84
    ¡
    0.84
    ŀ
    0.83
    ú
    0.83
    IJ
    0.81
    ĭ
    0.81
    µ
    0.79
    Activations Density 0.012%

    No Known Activations