© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14794
    Prev
    Next
    INDEX
    Explanations

    medical terms and related information

    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
    +0.16
    0.7%
    508
    +0.11
    0.5%
    149
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.16
    0.04
    290
    +0.11
    0.03
    524
    +0.10
    0.03
    Negative Logits
    xual
    -0.92
    uble
    -0.85
    gger
    -0.78
     Grayson
    -0.76
    unin
    -0.76
    egg
    -0.75
    cair
    -0.73
    yip
    -0.72
    Publisher
    -0.70
     capped
    -0.69
    POSITIVE LOGITS
     practition
    1.11
     marijuana
    1.04
     care
    0.98
     practitioner
    0.96
     diagnoses
    0.94
     Marijuana
    0.94
     treatments
    0.94
     doctor
    0.93
     diagnosis
    0.93
     practitioners
    0.92
    Activations Density 0.035%

    No Known Activations