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. 23846
    Prev
    Next
    INDEX
    Explanations

    references to various types of stores

    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
    459
    +0.13
    0.6%
    167
    +0.12
    0.5%
    75
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.13
    0.03
    459
    +0.12
    0.03
    114
    +0.12
    0.03
    Negative Logits
    ersen
    -0.75
    SHIP
    -0.75
    vernment
    -0.74
    theless
    -0.73
    vous
    -0.73
    param
    -0.71
     Caucus
    -0.66
    ansson
    -0.65
    emonic
    -0.65
    utan
    -0.64
    POSITIVE LOGITS
     shelves
    1.15
    houses
    0.98
     store
    0.95
     stores
    0.95
     clerk
    0.95
    stores
    0.93
     malls
    0.92
    store
    0.92
    keepers
    0.92
     storefront
    0.91
    Activations Density 0.034%

    No Known Activations