© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    information related to biographies or news articles about a specific person

    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
    672
    +0.12
    0.6%
    489
    +0.10
    0.5%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.02
    314
    +0.10
    0.00
    530
    +0.10
    0.02
    Negative Logits
    istor
    -0.87
    ruary
    -0.81
    heit
    -0.81
    ieu
    -0.78
    dor
    -0.76
    essee
    -0.71
    eus
    -0.68
    loe
    -0.68
    ulic
    -0.67
    eph
    -0.66
    POSITIVE LOGITS
    ©¶æ
    0.94
     Larson
    0.70
     transcription
    0.69
    èª
    0.68
    ij士
    0.67
    Īè
    0.67
     millenn
    0.64
     Kramer
    0.63
    ThumbnailImage
    0.62
    çīĪ
    0.62
    Activations Density 0.142%

    No Known Activations