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. 23928
    Prev
    Next
    INDEX
    Explanations

    references to professional golf tournaments and related statistics

    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
    373
    +0.15
    0.7%
    337
    +0.09
    0.4%
    147
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.02
    406
    +0.09
    0.02
    326
    +0.09
    0.02
    Negative Logits
    hra
    -0.75
    aram
    -0.73
    byn
    -0.69
    gian
    -0.68
     disag
    -0.68
    bh
    -0.67
    bats
    -0.65
    mr
    -0.63
    gew
    -0.63
    mble
    -0.63
    POSITIVE LOGITS
    Maps
    0.81
    Arcade
    0.78
    Cola
    0.72
     Fiesta
    0.72
    Magazine
    0.71
     Arcade
    0.69
    Vision
    0.66
    Cop
    0.66
    West
    0.66
     Surge
    0.66
    Activations Density 0.040%

    No Known Activations