© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    brand names related to beverages

    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
    569
    +0.10
    0.5%
    67
    +0.10
    0.5%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.10
    0.01
    107
    +0.10
    0.01
    631
    +0.10
    0.01
    Negative Logits
     Leilan
    -0.72
     CPC
    -0.70
     writ
    -0.65
     innocence
    -0.64
     Sons
    -0.63
    manship
    -0.62
     Corpus
    -0.60
     PDT
    -0.60
     Legion
    -0.60
     FAA
    -0.59
    POSITIVE LOGITS
    tesque
    1.43
    cery
    1.31
    ovy
    1.30
    veland
    1.13
    ggy
    1.12
    lean
    1.09
    ove
    1.08
    tty
    1.04
    hett
    1.03
    ogle
    1.03
    Activations Density 0.011%

    No Known Activations