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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10246
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare policies and Medicaid

    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
    288
    +0.17
    0.8%
    481
    +0.15
    0.7%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.02
    508
    +0.15
    0.02
    444
    +0.12
    0.02
    Negative Logits
    semble
    -0.86
    pole
    -0.74
    ths
    -0.70
    cold
    -0.70
    lihood
    -0.70
    lang
    -0.70
    hu
    -0.68
    */(
    -0.68
    lass
    -0.68
    axe
    -0.67
    POSITIVE LOGITS
     reimbursement
    1.03
     eligibility
    1.01
     beneficiaries
    0.98
     reimburse
    0.96
     Advantage
    0.90
     Benefits
    0.89
     rebate
    0.86
     enrollment
    0.85
     expansion
    0.85
     recipients
    0.83
    Activations Density 0.055%

    No Known Activations