© 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. 3718
    Prev
    Next
    INDEX
    Explanations

    information related to a specific event or location, specifically the Las Vegas shooting incident involving Stephen Paddock

    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
    288
    +0.17
    0.8%
    649
    +0.11
    0.5%
    757
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.17
    0.01
    147
    +0.11
    0.01
    211
    +0.11
    0.01
    Negative Logits
     streng
    -0.77
     facult
    -0.76
    omaly
    -0.75
    ocide
    -0.71
    boards
    -0.70
    work
    -0.67
    istry
    -0.67
    arist
    -0.67
    atures
    -0.67
    author
    -0.65
    POSITIVE LOGITS
     Vegas
    1.02
     casinos
    1.00
     Sands
    0.97
     Metropolitan
    0.89
     Boulevard
    0.89
     Lumpur
    0.85
     casino
    0.83
     Strip
    0.83
     Casino
    0.80
     Hilton
    0.80
    Activations Density 0.020%

    No Known Activations