© 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. 15094
    Prev
    Next
    INDEX
    Explanations

    phrases related to sacrifice

    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
    347
    +0.11
    0.5%
    406
    +0.11
    0.5%
    19
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.11
    0.01
    347
    +0.11
    0.01
    332
    +0.11
    0.01
    Negative Logits
     Wonderland
    -0.73
     Roosevelt
    -0.68
    è¦ļéĨĴ
    -0.68
    NING
    -0.68
    backer
    -0.67
    DonaldTrump
    -0.66
    agher
    -0.65
    ãĥī
    -0.64
     Cheong
    -0.64
     Clarkson
    -0.61
    POSITIVE LOGITS
    ificial
    1.29
    rament
    1.29
    char
    1.14
    rifice
    1.11
    het
    1.06
    anus
    1.03
    rum
    0.99
    ram
    0.98
    raf
    0.96
    iety
    0.96
    Activations Density 0.018%

    No Known Activations