© 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. 15100
    Prev
    Next
    INDEX
    Explanations

    the word "all"

    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
    71
    +0.12
    0.5%
    157
    +0.10
    0.5%
    619
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    619
    +0.12
    0.04
    157
    +0.10
    0.04
    126
    +0.10
    0.03
    Negative Logits
    inth
    -0.81
    assembly
    -0.66
    yip
    -0.64
     Rouge
    -0.63
    hift
    -0.63
    lift
    -0.59
    warming
    -0.59
    fw
    -0.58
    FH
    -0.57
    xit
    -0.57
    POSITIVE LOGITS
    ocating
    1.26
    ocated
    1.06
    usions
    1.05
    igators
    1.04
     kinds
    1.03
    iances
    1.00
    uding
    0.99
     sorts
    0.98
    edged
    0.95
     vying
    0.94
    Activations Density 0.069%

    No Known Activations