© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    phrases related to gardening and natural organic practices

    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
    408
    +0.14
    0.6%
    257
    +0.11
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.08
    257
    +0.11
    0.06
    29
    +0.11
    0.07
    Negative Logits
    orge
    -0.79
    anamo
    -0.71
    glass
    -0.68
    hemy
    -0.66
    enda
    -0.66
    Film
    -0.66
    eth
    -0.66
    roth
    -0.65
     awa
    -0.63
    aram
    -0.61
    POSITIVE LOGITS
     lieu
    0.79
     whichever
    0.76
     hopes
    0.75
     accordance
    0.73
     whence
    0.72
     anticipation
    0.69
    tnc
    0.69
     evenings
    0.68
     regards
    0.67
     order
    0.65
    Activations Density 0.535%

    No Known Activations