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 3072
    5. 8-RES_FS3072-JB
    6. 1857
    Prev
    Next
    INDEX
    Explanations

    invitations to events and announcements with specific dates and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    166
    +0.10
    0.4%
    339
    +0.09
    0.4%
    23
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.08
    659
    +0.09
    0.07
    326
    +0.09
    0.08
    Negative Logits
    vous
    -0.90
    iders
    -0.71
    analysis
    -0.68
    OME
    -0.68
    ATES
    -0.63
    Ö¼
    -0.62
    dayName
    -0.62
    actionDate
    -0.61
    ider
    -0.61
    caps
    -0.61
    POSITIVE LOGITS
    achment
    1.09
    inen
    0.98
    ributes
    0.94
    ention
    0.94
    erers
    0.92
    erer
    0.91
     Arbor
    0.90
    raction
    0.89
    orney
    0.88
    leground
    0.84
    Activations Density 1.130%

    No Known Activations