© 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. 15515
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to the Zika virus

    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
    481
    +0.13
    0.6%
    286
    +0.10
    0.4%
    200
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    181
    +0.10
    0.01
    343
    +0.10
    0.01
    Negative Logits
    Reviewer
    -0.99
     actionGroup
    -0.85
    anguage
    -0.80
    istered
    -0.79
    iber
    -0.78
    oway
    -0.76
    umn
    -0.73
    ony
    -0.72
    udic
    -0.71
    ogy
    -0.71
    POSITIVE LOGITS
     virus
    0.89
     Virus
    0.73
     mosquit
    0.68
     boosters
    0.66
     booster
    0.65
     Braz
    0.65
     Zika
    0.65
     Grande
    0.64
     contamin
    0.63
     contaminated
    0.62
    Activations Density 0.023%

    No Known Activations