© 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. 14890
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Liberty"

    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
    +0.17
    0.8%
    99
    +0.12
    0.5%
    398
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.02
    99
    +0.12
    0.01
    394
    +0.09
    0.01
    Negative Logits
    soDeliveryDate
    -0.94
    uggest
    -0.70
     traumatic
    -0.66
    ãĤĭ
    -0.65
    orde
    -0.64
    lined
    -0.62
     reconc
    -0.61
    endered
    -0.61
     Mehran
    -0.61
    ynthesis
    -0.61
    POSITIVE LOGITS
    tarian
    0.94
    tarians
    0.84
    ously
    0.84
     Amendments
    0.81
    othal
    0.79
     Mutual
    0.74
    ibility
    0.73
     Liberty
    0.71
    fulness
    0.69
    fighter
    0.69
    Activations Density 0.017%

    No Known Activations