© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    references to parenting and family-related activities

    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
    331
    +0.09
    0.4%
    212
    +0.09
    0.4%
    322
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.09
    0.08
    43
    +0.09
    0.07
    297
    +0.08
    0.07
    Negative Logits
    ulner
    -0.72
    ursive
    -0.72
    vae
    -0.69
    rius
    -0.68
    itionally
    -0.66
    ensed
    -0.65
    atively
    -0.65
    ently
    -0.62
     guiActiveUn
    -0.62
    epend
    -0.61
    POSITIVE LOGITS
     haha
    1.08
     etc
    1.01
     huh
    0.98
     eh
    0.96
     anyways
    0.82
     LOL
    0.82
     lest
    0.81
     lol
    0.81
     blah
    0.78
     fries
    0.76
    Activations Density 0.393%

    No Known Activations