Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 294
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports teams

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    373
    +0.14
    0.7%
    41
    +0.10
    0.5%
    298
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.09
    232
    +0.10
    0.17
    659
    +0.10
    0.14
    Negative Logits
    catentry
    -0.82
    REDACTED
    -0.67
    ascript
    -0.67
     Predator
    -0.66
    Ö¼
    -0.66
    UCT
    -0.66
    PRES
    -0.60
     DRAG
    -0.59
     priceless
    -0.59
    ãĥīãĥ©
    -0.57
    POSITIVE LOGITS
    puff
    0.88
    ĵĺ
    0.84
    itzer
    0.81
    coe
    0.80
    erville
    0.79
    emouth
    0.79
    inki
    0.78
    erton
    0.73
    leck
    0.71
    reau
    0.69
    Activations Density 5.200%

    No Known Activations