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. 23786
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of 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
    393
    +0.11
    0.5%
    373
    +0.10
    0.5%
    557
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    557
    +0.11
    0.02
    611
    +0.10
    0.02
    409
    +0.10
    0.02
    Negative Logits
    dayName
    -0.79
    ettel
    -0.60
    jo
    -0.60
    Preview
    -0.59
    =-=-=-=-=-=-=-=-
    -0.58
    uyomi
    -0.58
    gee
    -0.58
    pmwiki
    -0.57
    asma
    -0.56
    irs
    -0.56
    POSITIVE LOGITS
     us
    0.83
     eternity
    0.82
     humankind
    0.79
     humanity
    0.77
     mankind
    0.77
    worldly
    0.72
     existence
    0.68
     HuffPost
    0.66
     society
    0.65
     life
    0.65
    Activations Density 0.043%

    No Known Activations