© 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. 19445
    Prev
    Next
    INDEX
    Explanations

    names of characters from a specific story or series

    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
    481
    +0.15
    0.7%
    447
    +0.13
    0.6%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.04
    326
    +0.13
    0.04
    543
    +0.11
    0.04
    Negative Logits
    Reviewer
    -0.74
    EPA
    -0.74
    utra
    -0.73
    hower
    -0.71
    Islamic
    -0.69
    liga
    -0.66
    iterranean
    -0.66
    tml
    -0.65
    uph
    -0.64
    inline
    -0.64
    POSITIVE LOGITS
     Granger
    0.95
     Kenobi
    0.90
     Weasley
    0.84
     Bagg
    0.82
     Sparkle
    0.82
     kidnapped
    0.81
     Osw
    0.81
     Lann
    0.80
     abducted
    0.80
     herself
    0.78
    Activations Density 0.172%

    No Known Activations