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 24576
    5. 8-RES_FS24576-JB
    6. 23528
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and related prepositional phrases

    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
    413
    +0.10
    0.5%
    393
    +0.10
    0.4%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.04
    362
    +0.10
    0.03
    413
    +0.09
    0.03
    Negative Logits
    ĸļ
    -0.78
    alez
    -0.76
    hesis
    -0.75
    chart
    -0.74
    onent
    -0.74
    think
    -0.73
    ertodd
    -0.73
    ula
    -0.73
    picture
    -0.71
    hement
    -0.71
    POSITIVE LOGITS
     impending
    1.25
     imminent
    1.01
     wrongdoing
    1.01
     layoffs
    0.91
     inacc
    0.89
     displacement
    0.86
     persecution
    0.85
     widespread
    0.80
     possible
    0.79
     sightings
    0.79
    Activations Density 0.121%

    No Known Activations