© 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 24576
    9. 8-RES_FS24576-JB
    11. 18924
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and broadcasts

    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
    649
    +0.09
    0.4%
    362
    +0.09
    0.4%
    685
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.09
    0.04
    269
    +0.09
    0.04
    685
    +0.09
    0.03
    Negative Logits
    acter
    -0.82
    mere
    -0.72
    rious
    -0.71
    ean
    -0.69
    ynt
    -0.68
    lement
    -0.68
    ternity
    -0.67
    aniel
    -0.66
    MpServer
    -0.65
    zsche
    -0.64
    POSITIVE LOGITS
     behalf
    1.15
    screen
    1.02
    demand
    0.99
     Demand
    0.97
     Sundays
    0.96
     Mondays
    0.96
     Saturdays
    0.94
     Fridays
    0.93
     YouTube
    0.91
     Youtube
    0.91
    Activations Density 0.124%

    No Known Activations