© 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 EvalsExportsinterp-engineNEWAPI 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. 16978
    Prev
    Next
    INDEX
    Explanations

    phrases related to health insurance, coverage policies, and governmental regulations

    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
    31
    +0.11
    0.5%
    481
    +0.10
    0.5%
    114
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.11
    0.03
    575
    +0.10
    0.03
    114
    +0.10
    0.03
    Negative Logits
     Hoo
    -0.73
    ovie
    -0.71
    cia
    -0.70
    oder
    -0.70
    lins
    -0.70
    oric
    -0.69
    REDACTED
    -0.68
    onnaissance
    -0.68
     Technique
    -0.68
    shire
    -0.67
    POSITIVE LOGITS
    amacare
    1.12
     rebate
    1.09
     premiums
    1.07
     uninsured
    1.06
     eligibility
    1.03
     providers
    1.00
     reimburse
    0.97
     provider
    0.95
     reimbursement
    0.95
     Medicaid
    0.94
    Activations Density 0.084%

    No Known Activations