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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1272
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotes involving emotions and personal relationships

    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
    742
    +0.11
    0.5%
    526
    +0.11
    0.5%
    279
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.01
    212
    +0.11
    0.08
    762
    +0.10
    0.13
    Negative Logits
    etheless
    -0.99
    surprisingly
    -0.86
    mittedly
    -0.79
    ItemTracker
    -0.76
     anecd
    -0.74
    prisingly
    -0.74
    xtap
    -0.72
     unsurprisingly
    -0.71
    uitive
    -0.70
     Cosponsors
    -0.70
    POSITIVE LOGITS
    !'"
    1.64
     â̦"
    1.52
    .'"
    1.50
    ',"
    1.49
    '."
    1.49
    '"
    1.48
    .")
    1.48
    ,'"
    1.45
    !".
    1.44
     ..."
    1.38
    Activations Density 3.038%

    No Known Activations