© 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. 8600
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific online platform or community named "Pirate Bay."

    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
    238
    +0.12
    0.5%
    339
    +0.11
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.12
    0.01
    326
    +0.11
    0.01
    288
    +0.10
    0.01
    Negative Logits
    gaard
    -0.85
    BOOK
    -0.78
    xual
    -0.74
    USER
    -0.73
    ELS
    -0.70
    claw
    -0.70
    ORGE
    -0.69
     Pixie
    -0.68
     ACTION
    -0.68
    naires
    -0.66
    POSITIVE LOGITS
    acy
    1.30
    acies
    1.25
    acles
    1.23
    atical
    1.19
    acet
    1.14
    acist
    1.10
    acists
    1.02
    aband
    1.00
    aten
    0.99
    andom
    0.99
    Activations Density 0.018%

    No Known Activations