© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25601
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jean" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    71
    +0.17
    0.9%
    369
    +0.17
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.17
    0.02
    71
    +0.17
    0.02
    59
    +0.14
    0.02
    Negative Logits
    irm
    -1.68
     present
    -1.67
    "?"
    -1.67
     recent
    -1.63
    ils
    -1.57
     former
    -1.57
     definite
    -1.54
    uties
    -1.54
    '">
    -1.54
     Russian
    -1.52
    POSITIVE LOGITS
    issance
    1.97
    uelle
    1.92
    quito
    1.87
    fried
    1.77
    finder
    1.72
    ató
    1.67
    osphere
    1.66
    icillin
    1.62
    opan
    1.62
    ilee
    1.61
    Activations Density 0.012%

    No Known Activations