© 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 24576
    9. 8-RES_FS24576-JB
    11. 220
    Prev
    Next
    INDEX
    Explanations

    words related to public health, disease control, and medical conditions

    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
    239
    +0.13
    0.6%
    360
    +0.12
    0.6%
    505
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.13
    0.01
    723
    +0.12
    0.01
    239
    +0.11
    0.01
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.79
    arov
    -0.71
    ettel
    -0.69
    hend
    -0.69
    hift
    -0.69
    reads
    -0.69
    sth
    -0.68
    rises
    -0.68
    igans
    -0.67
    Sov
    -0.67
    POSITIVE LOGITS
     Prevention
    0.91
     Diseases
    0.84
     Disease
    0.82
     infectious
    0.81
     Disorders
    0.80
     Tropical
    0.80
     Outbreak
    0.79
     Injury
    0.78
     Psychiatry
    0.77
     Medicine
    0.77
    Activations Density 0.027%

    No Known Activations