© 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. 12191
    Prev
    Next
    INDEX
    Explanations

    medical terms and school-related phrases

    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
    447
    +0.26
    1.2%
    481
    +0.14
    0.7%
    241
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.26
    0.06
    343
    +0.14
    0.06
    288
    +0.13
    0.07
    Negative Logits
    Materials
    -0.71
    agonists
    -0.71
    etimes
    -0.70
    agonist
    -0.67
    soType
    -0.66
    latable
    -0.65
    blance
    -0.65
    depending
    -0.63
    rawdownloadcloneembedreportprint
    -0.62
    properties
    -0.62
    POSITIVE LOGITS
     vs
    0.86
     versus
    0.83
     dominates
    0.81
     alone
    0.81
     fared
    0.74
     ($
    0.73
     occupies
    0.72
    ®,
    0.71
     ->
    0.71
     famously
    0.71
    Activations Density 0.491%

    No Known Activations