© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    conditional statements of action

    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
    86
    +0.10
    0.4%
    529
    +0.10
    0.4%
    203
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    529
    +0.10
    0.05
    300
    +0.10
    0.05
    582
    +0.08
    0.04
    Negative Logits
    Eye
    -0.77
     Deity
    -0.71
    ãĥŃ
    -0.70
    ude
    -0.69
    ryu
    -0.69
    chant
    -0.69
    orah
    -0.67
    ights
    -0.67
    venth
    -0.65
    hig
    -0.64
    POSITIVE LOGITS
     successful
    0.93
     unchecked
    0.90
     policymakers
    0.87
     elected
    0.83
     unsuccessful
    0.80
    fy
    0.77
     anything
    0.74
    soever
    0.71
     2020
    0.69
    rame
    0.69
    Activations Density 0.109%

    No Known Activations