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

    Neuronpedia

    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. 11982
    Prev
    Next
    INDEX
    Explanations

    phrases related to retirement and physical activities

    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
    468
    +0.11
    0.5%
    582
    +0.11
    0.5%
    267
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.11
    0.03
    267
    +0.11
    0.03
    468
    +0.11
    0.03
    Negative Logits
    toe
    -0.69
    TE
    -0.69
    tein
    -0.69
    leading
    -0.68
    Latin
    -0.67
    ilty
    -0.67
    orde
    -0.67
    SUP
    -0.66
    md
    -0.66
    PRES
    -0.64
    POSITIVE LOGITS
     suddenly
    0.98
     abruptly
    0.91
     again
    0.86
     mysteriously
    0.83
     comes
    0.81
     came
    0.77
     recons
    0.75
     proceeded
    0.75
     disappears
    0.74
     inexpl
    0.73
    Activations Density 0.056%

    No Known Activations