© 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. 22724
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of community and collective effort

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.35
    1.7%
    393
    +0.15
    0.7%
    81
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.35
    0.09
    362
    +0.15
    0.07
    570
    +0.10
    0.01
    Negative Logits
    ocre
    -0.70
    gyn
    -0.68
    atmeal
    -0.63
    ixties
    -0.62
    >,
    -0.61
    Bec
    -0.60
    ogi
    -0.60
    ocr
    -0.60
    word
    -0.59
    iron
    -0.59
    POSITIVE LOGITS
     accompanying
    0.81
     associated
    0.72
     eventual
    0.68
     recovery
    0.68
     attendant
    0.67
    lihood
    0.67
     resultant
    0.66
     consequ
    0.65
     attachments
    0.63
     ensuing
    0.62
    Activations Density 0.714%

    No Known Activations