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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1289
    Prev
    Next
    INDEX
    Explanations

    positive sentiments related to experiences or feelings of enjoyment

    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
    467
    +0.12
    0.5%
    725
    +0.09
    0.4%
    549
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.12
    0.02
    552
    +0.09
    0.02
    467
    +0.08
    0.02
    Negative Logits
    PATH
    -0.73
    soDeliveryDate
    -0.73
    arta
    -0.71
    ura
    -0.67
    Public
    -0.67
    rage
    -0.65
    vernment
    -0.62
    clinical
    -0.62
    Wr
    -0.61
    authorized
    -0.61
    POSITIVE LOGITS
     Flavoring
    0.88
     seeing
    0.74
     watching
    0.74
    lihood
    0.73
     reading
    0.73
     surprises
    0.69
     hearing
    0.68
     learning
    0.66
     chatting
    0.65
    liness
    0.65
    Activations Density 0.072%

    No Known Activations