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 24576
    5. 8-RES_FS24576-JB
    6. 19217
    Prev
    Next
    INDEX
    Explanations

    names and titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    393
    +0.21
    1.0%
    362
    +0.13
    0.6%
    526
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.03
    362
    +0.13
    0.03
    385
    +0.12
    0.03
    Negative Logits
    links
    -0.69
    gat
    -0.68
     Tasmania
    -0.67
    uten
    -0.66
    posts
    -0.64
     Albania
    -0.64
    rade
    -0.62
     Luffy
    -0.62
     Judaism
    -0.62
    aji
    -0.61
    POSITIVE LOGITS
     same
    1.42
     latter
    1.39
     aforementioned
    1.27
     entire
    1.22
     entirety
    1.14
    oret
    1.13
     slightest
    1.13
    ses
    1.13
     latest
    1.08
     whole
    1.06
    Activations Density 0.081%

    No Known Activations