© 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. 4760
    Prev
    Next
    INDEX
    Explanations

    names of colleges and universities

    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
    373
    +0.17
    0.8%
    727
    +0.10
    0.4%
    184
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.03
    176
    +0.10
    0.02
    500
    +0.09
    0.03
    Negative Logits
    ãĥķãĤ¡
    -0.65
    ––
    -0.60
    thumbnails
    -0.56
    piracy
    -0.56
     .)
    -0.55
    ODUCT
    -0.53
    ãĢ
    -0.53
    в
    -0.53
    âĢ
    -0.53
    âĸ
    -0.52
    POSITIVE LOGITS
     âĵĺ
    0.61
    endars
    0.57
    antam
    0.56
     Mechdragon
    0.55
     courts
    0.53
    akespeare
    0.52
     srf
    0.52
     etc
    0.51
    vernight
    0.51
    ĪĴ
    0.49
    Activations Density 0.154%

    No Known Activations