© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure codes

    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
    287
    +0.14
    0.8%
    478
    +0.13
    0.7%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.14
    0.01
    388
    +0.13
    0.02
    105
    +0.13
    0.01
    Negative Logits
    ĻĤ
    -2.04
    Ĺ
    -1.89
    Ł
    -1.85
    Ī
    -1.77
    §
    -1.73
    ¨
    -1.70
     victims
    -1.69
    ¼
    -1.68
    ı
    -1.65
    ĸ
    -1.64
    POSITIVE LOGITS
    chrotron
    1.77
    defer
    1.72
    nell
    1.65
    TRODUCTION
    1.54
    ambda
    1.51
    hbar
    1.49
    kered
    1.42
    fried
    1.37
    ourced
    1.36
    opropyl
    1.35
    Activations Density 0.090%

    No Known Activations