© 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. 6934
    Prev
    Next
    INDEX
    Explanations

    the repeated mention of the word "Quinn" in the text

    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
    651
    +0.13
    0.6%
    253
    +0.12
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    519
    +0.12
    0.01
    346
    +0.10
    0.01
    Negative Logits
    xual
    -0.79
    relevant
    -0.66
    rament
    -0.66
     fuels
    -0.66
    RAW
    -0.64
    ierrez
    -0.63
     marrow
    -0.62
     Harlem
    -0.62
    GGGGGGGG
    -0.60
    alde
    -0.60
    POSITIVE LOGITS
    spir
    0.94
     Quinn
    0.81
    pool
    0.79
    agan
    0.78
    sb
    0.77
    lich
    0.76
    ipeg
    0.75
    ifest
    0.74
    igan
    0.74
    pei
    0.74
    Activations Density 0.029%

    No Known Activations