© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    verbs expressing a command or advice

    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
    269
    +0.11
    0.5%
    314
    +0.10
    0.5%
    764
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.11
    0.02
    608
    +0.10
    0.03
    554
    +0.10
    0.01
    Negative Logits
    oslov
    -0.62
     implicated
    -0.61
     Emerging
    -0.58
    interstitial
    -0.56
     preceded
    -0.55
     Establishment
    -0.55
    ida
    -0.54
     Unable
    -0.54
     deployed
    -0.53
     RELE
    -0.53
    POSITIVE LOGITS
    ggles
    1.02
    pless
    0.93
    asting
    0.89
    lling
    0.86
    wered
    0.84
    asted
    0.83
    psy
    0.81
    perty
    0.80
    lled
    0.77
     pasture
    0.73
    Activations Density 0.073%

    No Known Activations