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 1536
    5. 8-RES_FS1536-JB
    6. 1388
    Prev
    Next
    INDEX
    Explanations

    text related to space exploration, analog simulation, and the activities surrounding these subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    267
    +0.09
    0.4%
    154
    +0.09
    0.4%
    711
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.09
    0.10
    247
    +0.09
    0.09
    708
    +0.09
    0.08
    Negative Logits
    ãĤ´ãĥ³
    -0.71
    depending
    -0.69
    matter
    -0.67
    leon
    -0.65
    romy
    -0.65
    abre
    -0.64
    stroke
    -0.64
     spoilers
    -0.62
    hawks
    -0.62
    hillary
    -0.62
    POSITIVE LOGITS
     (
    1.35
     ("
    1.24
     (?,
    1.10
     ('
    1.10
     ([
    1.08
     (&
    0.95
     (.
    0.95
     ()
    0.94
     [(
    0.93
     ({
    0.91
    Activations Density 2.219%

    No Known Activations