© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    information related to government regulations or legal proceedings

    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
    87
    +0.51
    2.8%
    547
    +0.10
    0.6%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.51
    -0.01
    680
    +0.10
    0.06
    756
    +0.09
    -0.04
    Negative Logits
     cows
    -0.57
     raping
    -0.55
    ocaust
    -0.54
    obyl
    -0.53
     monopol
    -0.53
    Virgin
    -0.51
     cunt
    -0.51
     cricket
    -0.51
     envy
    -0.51
     monog
    -0.50
    POSITIVE LOGITS
    endum
    0.74
     Weeks
    0.63
     conclud
    0.61
     HuffPost
    0.60
     Vance
    0.58
     narrowed
    0.56
     emailed
    0.56
     outlined
    0.54
     summarizes
    0.54
     RELE
    0.53
    Activations Density 1.628%

    No Known Activations