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 49152
    5. 8-RES_FS49152-JB
    6. 37145
    Prev
    Next
    INDEX
    Explanations

    references to the BlackBerry brand and its associated products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.16
    0.7%
    447
    +0.15
    0.7%
    481
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.16
    0.01
    359
    +0.15
    0.01
    484
    +0.13
    0.01
    Negative Logits
    oldemort
    -0.82
    Reviewer
    -0.82
    gyn
    -0.78
    igun
    -0.73
    uthor
    -0.73
    mble
    -0.71
    bilt
    -0.70
    urai
    -0.70
    ablishment
    -0.69
    severe
    -0.69
    POSITIVE LOGITS
    Berry
    1.07
     Wireless
    0.81
     Messenger
    0.80
     Safari
    0.80
    ®
    0.80
     smartphones
    0.79
     Nano
    0.73
     devices
    0.70
     phones
    0.70
    ®,
    0.69
    Activations Density 0.003%

    No Known Activations