© 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 49152
    9. 8-RES_FS49152-JB
    11. 41498
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    208
    +0.11
    0.5%
    459
    +0.09
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.11
    0.01
    208
    +0.09
    0.01
    754
    +0.09
    0.01
    Negative Logits
     Canaver
    -0.86
     Bord
    -0.80
     Hancock
    -0.75
    ibaba
    -0.73
    lda
    -0.70
    ĸļ
    -0.70
    hawks
    -0.68
     Bundy
    -0.68
    owicz
    -0.65
    pher
    -0.65
    POSITIVE LOGITS
    Delete
    0.76
    irmation
    0.72
    Delivery
    0.71
    Interstitial
    0.71
     elig
    0.71
     tenancy
    0.71
     subscription
    0.70
     renewal
    0.69
     Purchase
    0.69
     {*
    0.68
    Activations Density 0.015%

    No Known Activations