© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    mentions of iconic fictional villains, particularly from movies and TV shows

    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
    52
    +0.10
    0.5%
    306
    +0.10
    0.4%
    742
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.10
    0.01
    291
    +0.10
    0.01
    99
    +0.10
    0.01
    Negative Logits
    mble
    -1.09
    ÑĮ
    -0.79
    DonaldTrump
    -0.76
    ilk
    -0.74
    chell
    -0.74
    Ñı
    -0.72
    enza
    -0.72
    kson
    -0.71
    elsius
    -0.70
    ħĭ
    -0.69
    POSITIVE LOGITS
    esses
    1.10
    eye
    0.86
    toe
    0.81
    ess
    0.80
    otto
    0.80
     lions
    0.79
    heart
    0.79
    naire
    0.79
    fish
    0.79
    iasis
    0.78
    Activations Density 0.027%

    No Known Activations