© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20685
    Prev
    Next
    INDEX
    Explanations

    words related to military or defense activities

    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
    21
    +0.12
    0.5%
    288
    +0.10
    0.5%
    549
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.12
    0.02
    678
    +0.10
    0.02
    366
    +0.10
    0.02
    Negative Logits
    icol
    -0.77
    NESS
    -0.77
    oso
    -0.76
    icut
    -0.70
    IDA
    -0.69
    asar
    -0.69
     Luther
    -0.69
    icer
    -0.68
    inness
    -0.68
    umbnails
    -0.68
    POSITIVE LOGITS
    camp
    1.18
    plate
    0.99
    plates
    0.95
    ball
    0.91
    BALL
    0.82
     erosion
    0.82
    band
    0.80
    coat
    0.75
    balls
    0.71
    plan
    0.71
    Activations Density 0.025%

    No Known Activations