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. 43240
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "of."

    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
    79
    +0.10
    0.5%
    756
    +0.10
    0.5%
    126
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.10
    0.01
    664
    +0.10
    0.01
    611
    +0.10
    0.01
    Negative Logits
     Cosponsors
    -0.79
    ":["
    -0.74
     attm
    -0.72
    DERR
    -0.72
     largeDownload
    -0.72
     [&
    -0.71
    asking
    -0.69
     istg
    -0.69
    jee
    -0.68
    ername
    -0.68
    POSITIVE LOGITS
     Empires
    1.05
     reckoning
    0.94
     Wonders
    0.91
     Ultron
    0.86
     Enlightenment
    0.82
     Exploration
    0.80
     Invention
    0.80
     Apocalypse
    0.79
     maturity
    0.78
     Consent
    0.78
    Activations Density 0.019%

    No Known Activations