© 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. 15542
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to waking up

    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
    414
    +0.13
    0.6%
    372
    +0.13
    0.6%
    178
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.13
    0.02
    414
    +0.13
    0.02
    545
    +0.12
    0.02
    Negative Logits
    inates
    -0.78
    entric
    -0.73
    cer
    -0.67
    berus
    -0.66
    bis
    -0.64
    abwe
    -0.63
    regate
    -0.63
     Robertson
    -0.63
    orsi
    -0.62
     circumst
    -0.62
    POSITIVE LOGITS
    mares
    1.17
     refreshed
    0.99
     awake
    0.96
    up
    0.94
    wake
    0.92
    fulness
    0.89
    mare
    0.85
     up
    0.84
     woke
    0.83
    leep
    0.78
    Activations Density 0.018%

    No Known Activations