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. 611
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly related to news and politics

    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
    447
    +0.14
    0.7%
    668
    +0.12
    0.6%
    53
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.14
    502
    +0.12
    0.13
    46
    +0.10
    0.13
    Negative Logits
    Els
    -0.74
    Load
    -0.72
    oard
    -0.66
     Agric
    -0.62
    ories
    -0.61
    Ire
    -0.61
     Dominion
    -0.60
     Wem
    -0.60
    Georg
    -0.60
    Region
    -0.59
    POSITIVE LOGITS
     Jr
    1.39
     Sr
    1.11
     III
    1.06
     aka
    0.93
     famously
    0.93
    agher
    0.89
    Jr
    0.86
    's
    0.86
     himself
    0.82
    ovich
    0.82
    Activations Density 2.050%

    No Known Activations