© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15106
    Prev
    Next
    INDEX
    Explanations

    words related to countries, historical events, and military actions, particularly related to Vietnam

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.6%
    199
    +0.10
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.14
    0.01
    288
    +0.10
    0.01
    251
    +0.10
    0.01
    Negative Logits
    */(
    -1.08
    heet
    -0.82
    essional
    -0.80
    rencies
    -0.75
    tered
    -0.75
    aukee
    -0.74
    lev
    -0.73
    imov
    -0.71
    TAG
    -0.69
    idges
    -0.69
    POSITIVE LOGITS
     Nguyen
    1.03
     vet
    0.82
     War
    0.82
     Veterans
    0.81
     Laos
    0.80
     Nam
    0.78
    ogue
    0.78
    oleon
    0.78
     Vietnam
    0.77
     vets
    0.77
    Activations Density 0.018%

    No Known Activations