© 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. 14843
    Prev
    Next
    INDEX
    Explanations

    phrases referring to options or considerations

    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
    402
    +0.13
    0.6%
    706
    +0.10
    0.5%
    494
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.03
    313
    +0.10
    0.03
    159
    +0.10
    0.03
    Negative Logits
    phabet
    -0.77
    odore
    -0.75
    ente
    -0.70
    ACTED
    -0.70
    anners
    -0.69
    heed
    -0.69
    ctor
    -0.69
    urden
    -0.68
    BuyableInstoreAndOnline
    -0.66
    oulos
    -0.64
    POSITIVE LOGITS
     respects
    1.22
     embodiments
    1.14
     cases
    1.11
     instances
    0.99
     jurisdictions
    0.98
     places
    0.97
     circumstances
    0.97
     circles
    0.96
     areas
    0.95
     contexts
    0.95
    Activations Density 0.051%

    No Known Activations