© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23913
    Prev
    Next
    INDEX
    Explanations

    content related to health risks associated with obesity and chronic diseases

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.14
    0.6%
    546
    +0.10
    0.5%
    252
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.14
    0.04
    252
    +0.10
    0.04
    428
    +0.10
    0.03
    Negative Logits
    soDeliveryDate
    -0.92
    selage
    -0.87
    Reviewer
    -0.81
    âķIJ
    -0.81
     Brands
    -0.80
     Companies
    -0.80
    ãĥĦ
    -0.77
    prises
    -0.77
    endor
    -0.76
    itures
    -0.76
    POSITIVE LOGITS
     disease
    1.46
     tuberculosis
    1.44
     dementia
    1.41
     illness
    1.38
     diseases
    1.38
     diabetes
    1.38
     malnutrition
    1.35
     asthma
    1.35
     arthritis
    1.35
     depression
    1.35
    Activations Density 0.173%

    No Known Activations