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. 23275
    Prev
    Next
    INDEX
    Explanations

    the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.28
    1.4%
    393
    +0.18
    0.9%
    385
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.28
    0.07
    608
    +0.18
    0.07
    362
    +0.13
    0.06
    Negative Logits
    thood
    -0.73
    Ò
    -0.71
    imi
    -0.69
    ãĤĭ
    -0.68
    ceive
    -0.68
    !.
    -0.66
    Ïī
    -0.65
    plete
    -0.65
    tumblr
    -0.64
    greg
    -0.63
    POSITIVE LOGITS
     idea
    1.07
    oret
    1.04
     timing
    1.04
     biggest
    1.00
     situation
    0.99
     absence
    0.99
     latter
    0.99
     entire
    0.98
     notion
    0.97
     discrepancy
    0.97
    Activations Density 0.266%

    No Known Activations