© 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 12288
    9. 8-RES_FS12288-JB
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    words related to military operations and procedures

    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
    373
    +0.09
    0.4%
    308
    +0.09
    0.4%
    598
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.03
    192
    +0.09
    0.02
    288
    +0.09
    0.04
    Negative Logits
     language
    -0.80
    eries
    -0.79
    rums
    -0.75
    */(
    -0.75
     whisk
    -0.73
    ictions
    -0.72
     sentence
    -0.72
    dylib
    -0.68
    bery
    -0.68
    NRS
    -0.68
    POSITIVE LOGITS
     Arrow
    0.93
     Pillar
    0.90
     Zero
    0.90
    olon
    0.83
     Rescue
    0.83
     Awesome
    0.81
     Dign
    0.80
     Hood
    0.80
     Nost
    0.79
     Euph
    0.79
    Activations Density 0.162%

    No Known Activations