© 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 49152
    9. 8-RES_FS49152-JB
    11. 41718
    Prev
    Next
    INDEX
    Explanations

    references to emerging markets and economies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.17
    0.8%
    362
    +0.11
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.17
    0.01
    555
    +0.11
    0.01
    288
    +0.10
    0.01
    Negative Logits
    fax
    -0.89
    @#&
    -0.82
    bia
    -0.81
    ibur
    -0.78
    cise
    -0.73
    bley
    -0.72
    ifi
    -0.72
    imaru
    -0.71
    imar
    -0.68
    ogun
    -0.68
    POSITIVE LOGITS
     technologies
    0.96
     economies
    0.95
     Opportun
    0.87
     markets
    0.86
     democracies
    0.81
     talents
    0.80
     trends
    0.79
     alliances
    0.79
     talent
    0.79
     superpower
    0.78
    Activations Density 0.008%

    No Known Activations