© 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 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. 11091
    Prev
    Next
    INDEX
    Explanations

    mentions of religious leaders or figures

    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
    26
    +0.15
    0.7%
    210
    +0.12
    0.5%
    437
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.15
    0.02
    288
    +0.12
    0.02
    511
    +0.11
    0.01
    Negative Logits
    bang
    -0.83
    skirts
    -0.74
    hops
    -0.70
    uring
    -0.69
    visible
    -0.68
    efully
    -0.68
    cham
    -0.66
    mable
    -0.65
    bender
    -0.65
    rek
    -0.64
    POSITIVE LOGITS
    inals
    0.97
    ity
    0.94
    itatively
    0.80
    ITY
    0.79
    isks
    0.78
    INAL
    0.77
    esian
    0.76
     Cardinals
    0.75
     Newman
    0.73
     Fitzgerald
    0.72
    Activations Density 0.034%

    No Known Activations