© 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 49152
    9. 8-RES_FS49152-JB
    11. 25983
    Prev
    Next
    INDEX
    Explanations

    references to cardboard

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    276
    +0.12
    0.6%
    167
    +0.11
    0.5%
    450
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.01
    26
    +0.11
    0.01
    678
    +0.11
    0.01
    Negative Logits
    ivari
    -0.76
    ivating
    -0.74
    CVE
    -0.74
    inen
    -0.73
    chenko
    -0.71
    oren
    -0.71
    nings
    -0.71
    IFA
    -0.70
    nesota
    -0.69
    alez
    -0.69
    POSITIVE LOGITS
     cardboard
    1.12
     boxes
    1.12
     box
    1.00
     wrapper
    0.86
     tubes
    0.86
     tube
    0.84
     sleeves
    0.83
     containers
    0.82
     packaging
    0.81
     crates
    0.80
    Activations Density 0.003%

    No Known Activations