© 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 49152
    9. 8-RES_FS49152-JB
    11. 45443
    Prev
    Next
    INDEX
    Explanations

    terms related to physical or social penalties and ethical issues, particularly those relevant to counterfeiting and medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    591
    +0.13
    0.6%
    128
    +0.10
    0.4%
    568
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    568
    +0.10
    0.02
    588
    +0.09
    0.02
    Negative Logits
    FUL
    -0.94
    theless
    -0.73
     orally
    -0.71
    hower
    -0.70
    é¾įå
    -0.67
     Nicotine
    -0.67
    stellar
    -0.66
    LESS
    -0.66
     Marketable
    -0.65
    Ô
    -0.65
    POSITIVE LOGITS
    itives
    0.99
    zon
    0.91
    uction
    0.91
    glers
    0.88
    gers
    0.88
    stration
    0.86
    amation
    0.86
    ification
    0.86
    ancers
    0.86
    ifiers
    0.86
    Activations Density 0.057%

    No Known Activations