© 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. 24195
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in programming or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    314
    +0.16
    0.7%
    160
    +0.10
    0.5%
    199
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.16
    0.01
    160
    +0.10
    0.04
    309
    +0.10
    0.02
    Negative Logits
     dece
    -0.79
     Concord
    -0.70
     nodd
    -0.67
     deduct
    -0.66
     millenn
    -0.66
     Hung
    -0.65
     Ferr
    -0.63
     juggling
    -0.63
     Telegram
    -0.62
     htt
    -0.62
    POSITIVE LOGITS
    meta
    1.00
    ISO
    0.98
    DATA
    0.95
    #$
    0.94
    deb
    0.91
    cens
    0.91
    mods
    0.91
    INC
    0.90
    50
    0.89
    VA
    0.89
    Activations Density 0.088%

    No Known Activations