© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12759
    Prev
    Next
    INDEX
    Explanations

    references to Canada and its geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    410
    +0.15
    0.8%
    21
    +0.13
    0.7%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.15
    0.01
    410
    +0.13
    0.03
    226
    +0.11
    0.03
    Negative Logits
    lessly
    -2.14
    ayed
    -1.82
    ableness
    -1.77
    olean
    -1.55
    >$
    -1.53
    endo
    -1.50
    ly
    -1.50
     prayed
    -1.50
    idious
    -1.48
    lest
    -1.45
    POSITIVE LOGITS
     Saskatchewan
    2.05
     Ontario
    2.01
     province
    1.97
     provincial
    1.95
     provinces
    1.95
     Trudeau
    1.94
     Manit
    1.94
     Canada
    1.93
     Provincial
    1.88
     Centre
    1.87
    Activations Density 0.277%

    No Known Activations