© 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. 15104
    Prev
    Next
    INDEX
    Explanations

    elements related to everyday tasks and habits, as well as thoughts and experiences

    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
    447
    +0.18
    0.8%
    481
    +0.12
    0.6%
    255
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.18
    0.07
    724
    +0.12
    0.07
    575
    +0.12
    0.07
    Negative Logits
    amaz
    -0.70
    ateur
    -0.70
    trak
    -0.69
    Syrian
    -0.68
    ACP
    -0.68
    thumbnails
    -0.67
    asus
    -0.66
    ramid
    -0.63
    ahon
    -0.63
    funding
    -0.62
    POSITIVE LOGITS
     arising
    0.96
    mith
    0.96
     imaginable
    0.93
     affecting
    0.92
     involving
    0.90
     relating
    0.88
     arise
    0.87
    pring
    0.85
     resonate
    0.85
    pace
    0.83
    Activations Density 0.332%

    No Known Activations