© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22383
    Prev
    Next
    INDEX
    Explanations

    punctuation marks typically used to denote the end of thoughts or sections in written text

    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
    178
    +0.10
    0.5%
    333
    +0.09
    0.4%
    278
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.02
    156
    +0.09
    0.01
    308
    +0.09
    0.01
    Negative Logits
    ishly
    -0.84
    ellery
    -0.77
    ifying
    -0.73
    ified
    -0.69
    bye
    -0.64
     Debor
    -0.62
    eln
    -0.62
    bett
    -0.61
     conserv
    -0.61
     neighb
    -0.60
    POSITIVE LOGITS
    ::::::::
    0.96
    :{
    0.68
    âĸij
    0.66
    *:
    0.65
    IGHTS
    0.64
     Pis
    0.62
    warts
    0.61
    76561
    0.60
    Statement
    0.59
    BuyableInstoreAndOnline
    0.59
    Activations Density 0.028%

    No Known Activations