© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 24113
    Prev
    Next
    INDEX
    Explanations

    instances of the word "times" in various 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
    71
    +0.13
    0.6%
    651
    +0.13
    0.6%
    341
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.13
    0.04
    71
    +0.13
    0.03
    416
    +0.11
    0.03
    Negative Logits
    Reviewer
    -0.89
    XT
    -0.81
     heirs
    -0.75
    DIT
    -0.69
    Marginal
    -0.66
    andr
    -0.65
    ourt
    -0.65
    rats
    -0.63
    liction
    -0.62
    rera
    -0.62
    POSITIVE LOGITS
     consecut
    1.04
     throughout
    0.90
    points
    0.84
     apiece
    0.78
     during
    0.77
     before
    0.77
    coded
    0.71
    cale
    0.71
     since
    0.64
     thereafter
    0.63
    Activations Density 0.036%

    No Known Activations