© 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. 24027
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named Jean

    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
    410
    +0.21
    1.2%
    156
    +0.17
    1.0%
    369
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.03
    71
    +0.17
    0.03
    59
    +0.16
    0.02
    Negative Logits
     ages
    -1.64
     different
    -1.59
     current
    -1.58
    ordinate
    -1.56
     recent
    -1.53
    apers
    -1.51
     ago
    -1.50
    "?"
    -1.49
     results
    -1.45
    uture
    -1.43
    POSITIVE LOGITS
    issance
    2.31
    stadt
    2.08
    ignon
    1.99
    aline
    1.96
    owski
    1.85
    fried
    1.84
    stown
    1.82
    ette
    1.76
    osphere
    1.75
    icillin
    1.73
    Activations Density 0.113%

    No Known Activations