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. 12089
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Karp."

    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
    7
    +0.13
    0.6%
    729
    +0.12
    0.5%
    42
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.13
    0.01
    659
    +0.12
    0.01
    701
    +0.11
    0.01
    Negative Logits
    ãģŁ
    -0.68
     Coke
    -0.67
    FUL
    -0.67
    gie
    -0.65
     Gallup
    -0.61
     Schumer
    -0.61
     Crist
    -0.61
     unequ
    -0.60
    kai
    -0.59
     Valent
    -0.58
    POSITIVE LOGITS
    olitics
    1.21
    iece
    1.05
    onent
    0.99
    odcast
    0.98
    acing
    0.97
    oons
    0.96
    athy
    0.95
    edia
    0.94
    retty
    0.94
    ools
    0.94
    Activations Density 0.008%

    No Known Activations