Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    the word "ose" 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_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
    59
    +0.13
    0.6%
    99
    +0.11
    0.5%
    661
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    579
    +0.11
    0.01
    59
    +0.10
    0.01
    Negative Logits
    icum
    -0.77
    oola
    -0.77
    agne
    -0.75
    rators
    -0.72
    azon
    -0.71
    arios
    -0.71
    DERR
    -0.70
    erest
    -0.68
    ersen
    -0.68
    naires
    -0.68
    POSITIVE LOGITS
    cond
    1.19
    lect
    1.13
    velt
    1.09
    idon
    1.02
    lihood
    0.94
    ph
    0.91
    bands
    0.89
    vich
    0.87
    eker
    0.84
    ppel
    0.83
    Activations Density 0.008%

    No Known Activations