© 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. 22369
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to the word "of."

    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
    218
    +0.12
    0.6%
    242
    +0.11
    0.5%
    133
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.12
    0.02
    133
    +0.11
    0.02
    755
    +0.10
    0.02
    Negative Logits
    asca
    -0.80
     Cosponsors
    -0.67
     Parables
    -0.67
    erella
    -0.65
    overe
    -0.62
    ynes
    -0.61
    erers
    -0.61
    alties
    -0.60
    Phill
    -0.60
    inge
    -0.59
    POSITIVE LOGITS
     October
    0.91
     late
    0.91
     December
    0.89
     November
    0.88
     September
    0.87
     June
    0.85
     January
    0.85
     July
    0.84
     August
    0.84
     April
    0.83
    Activations Density 0.025%

    No Known Activations