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. 1164
    Prev
    Next
    INDEX
    Explanations

    information related to sports events and athlete updates

    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
    87
    +0.17
    0.8%
    579
    +0.10
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.17
    -0.09
    579
    +0.10
    0.08
    634
    +0.10
    0.10
    Negative Logits
    iga
    -0.63
     Prix
    -0.55
    ãĤ´ãĥ³
    -0.52
     indexes
    -0.51
    STDOUT
    -0.51
     Allied
    -0.50
     climax
    -0.48
     CRC
    -0.48
    ).[
    -0.48
    bia
    -0.47
    POSITIVE LOGITS
     ..."
    1.36
     â̦"
    1.16
     [/
    1.14
    [/
    1.13
     ['
    1.07
    sic
    1.03
    ?'
    1.02
     @
    0.98
     [
    0.98
     [-
    0.94
    Activations Density 5.219%

    No Known Activations