© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    web links ending with ".html"

    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
    395
    +0.10
    0.4%
    477
    +0.09
    0.4%
    326
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.10
    0.02
    326
    +0.09
    0.01
    165
    +0.09
    0.01
    Negative Logits
     governors
    -0.83
    manship
    -0.75
     favor
    -0.69
     imperson
    -0.68
     democracies
    -0.68
     favour
    -0.67
     holog
    -0.67
     peripher
    -0.67
     overfl
    -0.66
     practices
    -0.66
    POSITIVE LOGITS
    #
    1.18
    tml
    1.09
    ttp
    0.99
    /?
    0.96
     Accessed
    0.89
    [/
    0.86
     =================================================================
    0.85
    html
    0.85
     Mehran
    0.84
     CrossRef
    0.81
    Activations Density 0.020%

    No Known Activations