© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18017
    Prev
    Next
    INDEX
    Explanations

    occurring patterns of duplicated phrases for emphasis

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.13
    0.7%
    393
    +0.10
    0.5%
    525
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.13
    0.02
    738
    +0.10
    0.01
    28
    +0.10
    0.01
    Negative Logits
    aimon
    -0.68
    MET
    -0.65
    eele
    -0.64
     Comet
    -0.57
    arthed
    -0.56
    runners
    -0.56
    ãĥŃ
    -0.55
    uality
    -0.55
    afety
    -0.55
    gat
    -0.54
    POSITIVE LOGITS
     main
    0.73
     same
    0.65
     ARTICLE
    0.65
     latest
    0.64
     slideshow
    0.64
     Advertisement
    0.64
     entire
    0.63
    content
    0.62
    ERY
    0.62
     whole
    0.61
    Activations Density 0.014%

    No Known Activations