© 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 12288
    9. 8-RES_FS12288-JB
    11. 822
    Prev
    Next
    INDEX
    Explanations

    words related to military conflicts and invasions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.14
    0.6%
    288
    +0.11
    0.5%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.05
    181
    +0.11
    0.03
    263
    +0.10
    0.03
    Negative Logits
    tle
    -0.83
    spot
    -0.77
    affer
    -0.74
    uctor
    -0.73
    MpServer
    -0.72
    nown
    -0.70
    role
    -0.70
    chem
    -0.68
    chel
    -0.67
    Sym
    -0.66
    POSITIVE LOGITS
    naires
    0.92
     Yamato
    0.88
     invasion
    0.84
     conquered
    0.82
     armies
    0.82
     Barbarian
    0.81
     conquest
    0.81
     Colonial
    0.80
     colonization
    0.80
     subjug
    0.79
    Activations Density 0.187%

    No Known Activations