© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 23912
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the word "all."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    194
    +0.12
    0.7%
    492
    +0.12
    0.7%
    220
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.07
    220
    +0.12
    0.06
    492
    +0.12
    0.06
    Negative Logits
    ¹
    -2.91
    ±
    -2.90
    ¯
    -2.71
    ®
    -2.68
    ŀ
    -2.67
    ·
    -2.66
    ¢
    -2.66
    Ķ
    -2.65
    ¿
    -2.64
    «
    -2.61
    POSITIVE LOGITS
    ograft
    2.16
    iances
    2.04
    usions
    1.95
     sorts
    1.93
    uded
    1.92
    erg
    1.88
    owing
    1.71
     kinds
    1.67
     hopes
    1.64
    uding
    1.63
    Activations Density 0.261%

    No Known Activations