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. 1616
    Prev
    Next
    INDEX
    Explanations

    historical facts and information

    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
    480
    +0.65
    3.9%
    447
    +0.21
    1.3%
    266
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.65
    0.04
    266
    +0.21
    0.24
    195
    +0.17
    0.01
    Negative Logits
    *.
    -0.49
    farious
    -0.49
    azard
    -0.47
    ilaterally
    -0.45
    undreds
    -0.44
    iership
    -0.43
    ãĥª
    -0.42
    efe
    -0.41
    abal
    -0.41
    interstitial
    -0.41
    POSITIVE LOGITS
     however
    0.91
     therefore
    0.80
     moreover
    0.74
     meanwhile
    0.71
     furthermore
    0.67
     also
    0.60
     tho
    0.57
     accordingly
    0.55
     additionally
    0.55
     though
    0.51
    Activations Density 7.048%

    No Known Activations