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. 23831
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts

    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
    393
    +0.19
    0.9%
    362
    +0.18
    0.9%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.08
    608
    +0.18
    0.06
    393
    +0.15
    0.06
    Negative Logits
    SPONSORED
    -0.80
    zon
    -0.77
     Leilan
    -0.74
    abouts
    -0.74
    Sec
    -0.73
     besides
    -0.71
     alone
    -0.70
    tackle
    -0.70
    Scotland
    -0.68
    Malley
    -0.67
    POSITIVE LOGITS
     same
    1.24
     notion
    1.07
     basics
    1.07
     concept
    1.06
     tenets
    1.04
     idea
    1.04
     premise
    1.03
     classic
    1.02
     original
    1.02
     simplest
    1.01
    Activations Density 0.212%

    No Known Activations