© 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. 7913
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to anatomical structures, especially those found in the brain and eyes

    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
    55
    +0.12
    0.6%
    255
    +0.12
    0.6%
    102
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.10
    55
    +0.12
    0.10
    566
    +0.12
    0.07
    Negative Logits
    addons
    -0.77
     congr
    -0.73
    tackle
    -0.71
    oice
    -0.70
    edin
    -0.69
    eering
    -0.68
    inav
    -0.68
     perks
    -0.67
     scares
    -0.67
    ionics
    -0.65
    POSITIVE LOGITS
     represented
    1.16
     characterized
    1.14
     assumed
    1.10
     shown
    1.08
     usually
    1.07
     regarded
    1.07
     depicted
    1.06
     comprised
    1.06
     analogous
    1.05
     considered
    1.05
    Activations Density 0.401%

    No Known Activations