© 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. 1375
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic regions, specifically Eastern European countries

    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
    494
    +0.11
    0.5%
    675
    +0.10
    0.5%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.11
    0.03
    288
    +0.10
    0.03
    65
    +0.09
    0.03
    Negative Logits
    bats
    -0.87
    renheit
    -0.81
    GUI
    -0.80
    VERTISEMENT
    -0.77
    pload
    -0.77
    asonable
    -0.76
    wik
    -0.76
    pass
    -0.75
    mouth
    -0.73
    mercial
    -0.73
    POSITIVE LOGITS
     countries
    1.33
     nations
    1.25
     Countries
    1.13
     dictators
    1.03
     Languages
    0.99
     region
    0.97
    istan
    0.95
     regions
    0.95
     kingdoms
    0.95
     languages
    0.94
    Activations Density 0.072%

    No Known Activations