© 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. 45480
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks, particularly focusing on quotation marks and parentheses

    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
    160
    +0.15
    0.7%
    385
    +0.13
    0.6%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.15
    0.05
    327
    +0.13
    0.03
    314
    +0.11
    0.01
    Negative Logits
     WHERE
    -0.73
    eday
    -0.73
     Tradable
    -0.71
     QC
    -0.66
     :)
    -0.65
     vom
    -0.64
     emphas
    -0.64
    ..................
    -0.63
     ðŁĻĤ
    -0.63
     McGr
    -0.63
    POSITIVE LOGITS
    own
    1.21
     own
    1.04
     inability
    1.04
    selves
    1.03
    latest
    0.99
     biggest
    0.96
     highest
    0.92
    original
    0.91
     absence
    0.91
    majority
    0.89
    Activations Density 0.127%

    No Known Activations