© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2928
    Prev
    Next
    INDEX
    Explanations

    phrases related to brewing companies and beverages

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    459
    +0.14
    0.6%
    48
    +0.11
    0.5%
    670
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.14
    0.02
    670
    +0.11
    0.02
    26
    +0.11
    0.02
    Negative Logits
    PsyNetMessage
    -0.81
    phia
    -0.78
     Telecommunications
    -0.77
    Downloadha
    -0.73
    ciating
    -0.69
    iane
    -0.69
     Payment
    -0.68
    MpServer
    -0.67
     partName
    -0.65
    essage
    -0.64
    POSITIVE LOGITS
     brewed
    1.31
    eries
    1.04
     brewing
    0.96
     brewer
    0.95
     beer
    0.93
     brewery
    0.92
     brew
    0.91
     cider
    0.90
     brewers
    0.89
    pub
    0.88
    Activations Density 0.036%

    No Known Activations