© 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. 15546
    Prev
    Next
    INDEX
    Explanations

    statements related to legal or criminal activities

    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
    6
    +0.15
    0.7%
    314
    +0.14
    0.6%
    675
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.15
    0.11
    675
    +0.14
    0.09
    37
    +0.10
    0.08
    Negative Logits
     imperson
    -0.83
     mushroom
    -0.83
     habit
    -0.82
     calcul
    -0.81
     controvers
    -0.80
     sprung
    -0.79
     camoufl
    -0.79
     range
    -0.78
     tricked
    -0.78
     resurrected
    -0.78
    POSITIVE LOGITS
    ï¸ı
    1.45
    ï¸
    1.08
    ¯
    1.03
    ÃĽ
    0.96
    dj
    0.91
    Reason
    0.89
    Disclaimer
    0.89
    Sources
    0.89
    ttp
    0.88
    Krist
    0.88
    Activations Density 0.189%

    No Known Activations