© 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. 19714
    Prev
    Next
    INDEX
    Explanations

    verbs besides 'to be' in progressive or continuous form

    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
    361
    +0.11
    0.5%
    73
    +0.10
    0.4%
    401
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.11
    0.04
    137
    +0.10
    0.03
    469
    +0.10
    0.03
    Negative Logits
    mson
    -0.74
    Enlarge
    -0.71
    ombies
    -0.70
    gyn
    -0.66
    paces
    -0.66
    bek
    -0.65
    usky
    -0.64
    gur
    -0.62
    oenix
    -0.62
    oooooooo
    -0.62
    POSITIVE LOGITS
     theirs
    0.94
     ours
    0.91
     hers
    0.87
     course
    0.86
     fare
    0.84
     sorts
    0.80
     yours
    0.77
     endeavor
    0.75
     reasoning
    0.73
     accommodation
    0.71
    Activations Density 0.118%

    No Known Activations