© 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. 15424
    Prev
    Next
    INDEX
    Explanations

    mentions of praise or compliments within written content

    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
    +0.40
    2.0%
    447
    +0.26
    1.3%
    481
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.40
    0.01
    266
    +0.26
    0.07
    498
    +0.14
    0.05
    Negative Logits
     alike
    -0.58
    é¾įå
    -0.58
    atever
    -0.54
    è¦ļéĨĴ
    -0.52
    entimes
    -0.52
     respectively
    -0.51
    idal
    -0.51
    foreign
    -0.51
    ¢
    -0.50
    ordinary
    -0.49
    POSITIVE LOGITS
     itself
    0.68
     Kers
    0.53
     retract
    0.53
     retracted
    0.52
     mov
    0.52
     Razer
    0.51
     foreskin
    0.51
     Farage
    0.50
     Pastebin
    0.50
     readable
    0.49
    Activations Density 0.658%

    No Known Activations