© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15082
    Prev
    Next
    INDEX
    Explanations

    the word "habit" or related words such as "habituall" or "habituation"

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    255
    +0.14
    0.7%
    285
    +0.10
    0.5%
    718
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    0.01
    666
    +0.10
    0.01
    596
    +0.10
    0.01
    Negative Logits
    zac
    -0.70
    ammy
    -0.68
    abad
    -0.66
    cross
    -0.66
    scl
    -0.64
    aucus
    -0.62
    yz
    -0.62
    equal
    -0.61
     SAR
    -0.61
    sie
    -0.59
    POSITIVE LOGITS
    ually
    1.12
    uation
    1.07
    uated
    1.07
     habits
    1.02
    uate
    0.90
     habit
    0.89
    uates
    0.78
    uating
    0.78
    spring
    0.76
    ality
    0.75
    Activations Density 0.018%

    No Known Activations