© 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. 277
    Prev
    Next
    INDEX
    Explanations

    narrative segments involving family or parenting situations, perhaps invoking emotions related to concern, care, and love

    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
    347
    +0.10
    0.5%
    610
    +0.10
    0.5%
    560
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.10
    0.07
    560
    +0.10
    0.04
    545
    +0.10
    0.04
    Negative Logits
     Customers
    -0.72
    tile
    -0.71
    éĹĺ
    -0.70
     Lobby
    -0.70
    ç
    -0.67
     Client
    -0.67
     Profit
    -0.67
    pex
    -0.67
    endiary
    -0.67
     Syndicate
    -0.67
    POSITIVE LOGITS
     kindergarten
    1.32
     preschool
    1.24
     nursery
    1.17
     puberty
    1.09
     todd
    0.99
     schooling
    0.97
     adulthood
    0.97
     daddy
    0.97
     adolescence
    0.97
     classmates
    0.96
    Activations Density 0.533%

    No Known Activations