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 768
    5. 8-RES_FS768-JB
    6. 38
    Prev
    Next
    INDEX
    Explanations

    quotations in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    314
    +0.24
    1.2%
    102
    +0.20
    1.0%
    442
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.24
    0.16
    160
    +0.20
    0.15
    442
    +0.17
    0.13
    Negative Logits
     Ross
    -0.78
     rental
    -0.75
     buoy
    -0.74
     matter
    -0.74
     editor
    -0.73
     accomp
    -0.73
     affiliate
    -0.72
     rall
    -0.71
     grasp
    -0.71
     Nieto
    -0.71
    POSITIVE LOGITS
    classic
    1.49
    true
    1.48
    normal
    1.47
    false
    1.47
    little
    1.46
    pure
    1.45
    every
    1.44
    double
    1.42
    traditional
    1.41
    almost
    1.41
    Activations Density 1.670%

    No Known Activations