© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    words related to visas and visa-related issues

    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
    575
    +0.15
    0.7%
    447
    +0.12
    0.6%
    343
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.15
    0.02
    343
    +0.12
    0.02
    0
    +0.12
    0.01
    Negative Logits
    ideshow
    -0.81
    icks
    -0.73
    landish
    -0.71
    sonian
    -0.71
     WATCHED
    -0.70
    yss
    -0.70
    tes
    -0.69
    oven
    -0.68
    Pie
    -0.67
    icles
    -0.65
    POSITIVE LOGITS
     versa
    1.41
     visas
    1.08
     visa
    1.07
     waiver
    1.01
     waivers
    0.91
     revoked
    0.90
     holders
    0.90
     lottery
    0.88
     holder
    0.82
     expired
    0.82
    Activations Density 0.022%

    No Known Activations