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. 732
    Prev
    Next
    INDEX
    Explanations

    user manuals or technical instructions

    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
    314
    +0.13
    0.6%
    442
    +0.10
    0.5%
    157
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.13
    0.18
    759
    +0.10
    0.17
    157
    +0.10
    0.18
    Negative Logits
     Samar
    -0.67
     Mobil
    -0.66
     Gmail
    -0.65
     Skydragon
    -0.62
     pressures
    -0.61
     Yor
    -0.61
     Democracy
    -0.60
     universities
    -0.59
     Mush
    -0.58
     towns
    -0.58
    POSITIVE LOGITS
    ï¸ı
    1.02
    ve
    1.01
    felt
    1.01
    ved
    1.00
    own
    0.99
    s
    0.99
    tal
    0.97
    t
    0.97
    agree
    0.96
    shall
    0.95
    Activations Density 0.994%

    No Known Activations