© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    events or incidents happening on specific days

    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
    383
    +0.10
    0.4%
    408
    +0.09
    0.4%
    504
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.03
    383
    +0.09
    0.03
    436
    +0.09
    0.02
    Negative Logits
    omer
    -0.79
    asive
    -0.78
    inav
    -0.75
    atts
    -0.70
    alach
    -0.70
    ipel
    -0.69
    rn
    -0.68
    ifled
    -0.67
    aution
    -0.66
    romeda
    -0.65
    POSITIVE LOGITS
     holidays
    0.85
     Thanksgiving
    0.76
    ieth
    0.73
    holiday
    0.72
     holiday
    0.71
    endment
    0.68
     anniversary
    0.67
     Halloween
    0.66
     arrival
    0.66
    lies
    0.65
    Activations Density 0.070%

    No Known Activations