Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 389
    Prev
    Next
    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    659
    +0.17
    0.8%
    471
    +0.12
    0.6%
    547
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.20
    232
    +0.12
    0.12
    284
    +0.10
    0.09
    Negative Logits
    âĶĢâĶĢ
    -0.77
    ··
    -0.74
    EEE
    -0.65
     MSG
    -0.64
    LEASE
    -0.62
     stock
    -0.61
    âĸ¬
    -0.61
     constant
    -0.60
    sburgh
    -0.60
     Californ
    -0.59
    POSITIVE LOGITS
    utsch
    1.08
    iani
    1.04
    oub
    1.01
    gaard
    0.96
    isner
    0.94
    ahl
    0.94
    inski
    0.93
    erman
    0.92
    assi
    0.90
    iso
    0.90
    Activations Density 0.788%

    No Known Activations