© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    names or words related to a specific person named "Kre"

    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
    670
    +0.13
    0.6%
    326
    +0.10
    0.5%
    585
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    326
    +0.10
    0.01
    525
    +0.10
    0.01
    Negative Logits
    ially
    -0.84
     Carbuncle
    -0.74
    IELD
    -0.74
    UCT
    -0.73
    eering
    -0.71
    ously
    -0.67
    iliary
    -0.66
    inals
    -0.65
     Casual
    -0.65
     defe
    -0.64
    POSITIVE LOGITS
    acher
    1.00
    pps
    0.94
    cks
    0.91
    ven
    0.90
    bs
    0.88
    elin
    0.87
    ffer
    0.87
    ppo
    0.84
    utz
    0.84
    pton
    0.83
    Activations Density 0.013%

    No Known Activations