© 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. 15493
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and civil rights discussions

    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
    480
    +0.23
    1.1%
    481
    +0.12
    0.6%
    86
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.23
    0.07
    351
    +0.12
    0.05
    737
    +0.12
    0.06
    Negative Logits
    ãĤ´ãĥ³
    -0.67
     Released
    -0.65
     Fey
    -0.60
     Whedon
    -0.59
    Born
    -0.59
    aru
    -0.57
    Synopsis
    -0.57
     Sai
    -0.57
     charms
    -0.57
    ãĤ¨ãĥ«
    -0.56
    POSITIVE LOGITS
    ,'"
    1.07
    ,"
    1.04
     [
    1.00
    ),"
    0.96
     deterrence
    0.95
    )."
    0.91
    ."
    0.89
    ,''
    0.88
     incent
    0.88
     legisl
    0.88
    Activations Density 0.977%

    No Known Activations