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. 46019
    Prev
    Next
    INDEX
    Explanations

    the word "while" in various contexts

    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
    726
    +0.13
    0.6%
    662
    +0.12
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.13
    0.02
    377
    +0.12
    0.02
    662
    +0.10
    0.02
    Negative Logits
    \\\\\\\\
    -0.69
    anic
    -0.69
    origin
    -0.68
    iquette
    -0.67
    DON
    -0.66
    emort
    -0.66
    met
    -0.65
    Nation
    -0.63
    %]
    -0.63
     reconc
    -0.63
    POSITIVE LOGITS
     ago
    0.90
     longer
    0.82
     Ago
    0.70
     smelling
    0.68
    iatus
    0.67
     hiatus
    0.65
    OOK
    0.64
    cium
    0.63
     sake
    0.63
     overdue
    0.61
    Activations Density 0.017%

    No Known Activations