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. 23356
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    102
    +0.20
    0.9%
    566
    +0.18
    0.9%
    55
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.10
    566
    +0.18
    0.09
    55
    +0.15
    0.10
    Negative Logits
    izes
    -0.77
     flourish
    -0.76
    pedia
    -0.71
     recommends
    -0.70
     Ensure
    -0.69
    inav
    -0.68
    ossom
    -0.67
    osate
    -0.67
     Highlights
    -0.66
     peaks
    -0.66
    POSITIVE LOGITS
     able
    1.09
     powerless
    1.03
     afraid
    1.02
     unable
    1.00
     willing
    0.98
     going
    0.97
     doing
    0.94
     aware
    0.94
     exercising
    0.92
     obligated
    0.92
    Activations Density 0.265%

    No Known Activations