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

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 10765
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Obamacare" and related discussions about health care legislation and insurance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.10
    0.4%
    646
    +0.10
    0.4%
    343
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.10
    0.03
    288
    +0.10
    0.03
    652
    +0.10
    0.02
    Negative Logits
    pole
    -0.92
    DragonMagazine
    -0.82
    ynt
    -0.78
    angular
    -0.76
    inent
    -0.74
    igi
    -0.73
    worldly
    -0.72
     maj
    -0.71
    ongh
    -0.71
    "]=>
    -0.71
    POSITIVE LOGITS
     repeal
    1.29
    amacare
    1.21
    Care
    0.99
     rollout
    0.97
     ObamaCare
    0.89
     enrollment
    0.87
     repealed
    0.87
     contraception
    0.84
     marketplace
    0.84
     premiums
    0.83
    Activations Density 0.082%

    No Known Activations