© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    information related to legal issues and controversies

    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
    164
    +0.14
    0.6%
    393
    +0.11
    0.5%
    464
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.14
    0.03
    530
    +0.11
    0.03
    176
    +0.10
    0.02
    Negative Logits
    oche
    -0.68
    eworks
    -0.68
    æ
    -0.67
    cffffcc
    -0.66
    !?"
    -0.66
    figured
    -0.66
    ,—
    -0.66
    {\
    -0.65
     likewise
    -0.65
    urion
    -0.65
    POSITIVE LOGITS
     etc
    1.04
     Tags
    1.02
     Miscellaneous
    0.88
     Unc
    0.81
     Retrieved
    0.81
     DOI
    0.77
     Misc
    0.75
     Silent
    0.70
     john
    0.67
    Wikipedia
    0.67
    Activations Density 0.101%

    No Known Activations