© 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. 18213
    Prev
    Next
    INDEX
    Explanations

    terms related to demographics, including specific groups and compositions

    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
    288
    +0.13
    0.6%
    235
    +0.09
    0.4%
    160
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.01
    724
    +0.09
    0.01
    575
    +0.09
    0.01
    Negative Logits
    pload
    -0.80
    ipedia
    -0.78
    ertodd
    -0.76
    nard
    -0.75
    amar
    -0.72
    ELS
    -0.71
    à
    -0.70
    isters
    -0.70
    shall
    -0.68
    mosp
    -0.65
    POSITIVE LOGITS
     demographic
    0.97
     demographics
    0.88
     profile
    0.87
     profiles
    0.84
     stereotype
    0.79
     makeup
    0.77
     indicators
    0.77
     characteristics
    0.75
     cues
    0.75
     shaping
    0.74
    Activations Density 0.024%

    No Known Activations