© 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 EvalsExportsinterp-engineNEWAPI 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. 13501
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and matters of fact

    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
    480
    +0.53
    2.8%
    481
    +0.13
    0.7%
    266
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.02
    362
    +0.13
    0.09
    266
    +0.12
    0.09
    Negative Logits
     unloaded
    -0.61
     subcontract
    -0.59
    assium
    -0.55
     deducted
    -0.55
    atto
    -0.55
    rection
    -0.53
     guessed
    -0.53
     replaced
    -0.53
    ById
    -0.53
    rition
    -0.53
    POSITIVE LOGITS
     fandom
    0.73
     genre
    0.66
     psyche
    0.65
     humankind
    0.64
     mainstream
    0.63
     contemporary
    0.63
     histor
    0.63
     dystopian
    0.63
     Souls
    0.62
     modern
    0.62
    Activations Density 1.035%

    No Known Activations