© 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. 15441
    Prev
    Next
    INDEX
    Explanations

    references to health-related topics, medical terms, and drug usage

    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
    256
    +0.09
    0.4%
    272
    +0.09
    0.4%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.09
    0.05
    362
    +0.09
    0.04
    331
    +0.09
    0.03
    Negative Logits
    ©¶æ¥µ
    -0.82
    interstitial
    -0.81
    ãĤ¨
    -0.73
    soon
    -0.72
     awoken
    -0.70
    éģ
    -0.70
    pei
    -0.69
     nonetheless
    -0.68
     +++
    -0.67
    10000
    -0.67
    POSITIVE LOGITS
     nor
    0.96
     necessarily
    0.96
     anymore
    0.87
     merits
    0.81
     malice
    0.76
     mere
    0.76
     overtly
    0.72
     individual
    0.71
     slightest
    0.69
     fancy
    0.69
    Activations Density 0.207%

    No Known Activations