© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12258
    Prev
    Next
    INDEX
    Explanations

    mentions of spokespersons or spokesmen in news articles

    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
    679
    +0.13
    0.6%
    373
    +0.12
    0.5%
    503
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.13
    0.03
    224
    +0.12
    0.03
    145
    +0.11
    0.03
    Negative Logits
    bows
    -0.77
    Winner
    -0.69
    iHUD
    -0.68
    rooms
    -0.66
    spir
    -0.66
    STEM
    -0.65
    1972
    -0.62
     dominance
    -0.61
    gam
    -0.61
    veyard
    -0.61
    POSITIVE LOGITS
     spokesman
    0.99
     spokesperson
    0.94
     emailed
    0.94
     spokeswoman
    0.93
    onse
    0.82
     clarified
    0.80
     waived
    0.77
     surn
    0.75
     contacted
    0.75
     statement
    0.75
    Activations Density 0.038%

    No Known Activations