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. 21596
    Prev
    Next
    INDEX
    Explanations

    names of people, places, and organizations

    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
    195
    +0.13
    0.6%
    578
    +0.12
    0.6%
    459
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.13
    0.03
    588
    +0.12
    0.02
    530
    +0.12
    0.02
    Negative Logits
    ¥ŀ
    -0.73
    è¦ļéĨĴ
    -0.68
     thumbnail
    -0.65
     stakes
    -0.62
     oats
    -0.61
    ruciating
    -0.60
    ishers
    -0.60
     galleries
    -0.59
    ¥µ
    -0.56
    osponsors
    -0.56
    POSITIVE LOGITS
    abeth
    1.31
    aurus
    1.15
    peed
    1.08
    earch
    1.06
    ource
    0.99
    rael
    0.98
    terness
    0.97
    pect
    0.95
    ection
    0.95
    aur
    0.95
    Activations Density 0.045%

    No Known Activations