© 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. 19600
    Prev
    Next
    INDEX
    Explanations

    names of a specific person – Jay

    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
    659
    +0.11
    0.5%
    630
    +0.10
    0.5%
    26
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.02
    630
    +0.10
    0.01
    443
    +0.10
    0.01
    Negative Logits
    milo
    -0.81
    iture
    -0.79
    ITIES
    -0.78
    ENTION
    -0.75
    htaking
    -0.73
    ACTED
    -0.70
    ancial
    -0.69
    idad
    -0.68
    IRE
    -0.66
    iments
    -0.65
    POSITIVE LOGITS
    hawks
    1.28
    hawk
    1.15
    walking
    1.01
    haw
    0.96
    lon
    0.93
    den
    0.92
    bird
    0.89
    Jay
    0.86
    jay
    0.86
    pee
    0.85
    Activations Density 0.011%

    No Known Activations