© 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. 700
    Prev
    Next
    INDEX
    Explanations

    phrases related to military activities and personnel

    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
    566
    +0.17
    0.8%
    288
    +0.13
    0.6%
    152
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.17
    0.04
    617
    +0.13
    0.03
    288
    +0.12
    0.03
    Negative Logits
    tions
    -0.76
    rics
    -0.74
    iaries
    -0.74
     Seller
    -0.72
    posed
    -0.70
    lations
    -0.69
    å£
    -0.69
    Oracle
    -0.69
    lus
    -0.67
    acles
    -0.67
    POSITIVE LOGITS
     Corps
    1.23
     barracks
    1.02
     colonel
    0.98
     fatig
    0.97
     corps
    0.95
     generals
    0.85
     garrison
    0.82
     stationed
    0.79
    alions
    0.79
     soldiers
    0.77
    Activations Density 0.069%

    No Known Activations