© 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. 1-RES-SM
    11. 26302
    Prev
    Next
    INDEX
    Explanations

    the word "Then" indicating a sequence or transition in narratives

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.26
    1.5%
    478
    +0.14
    0.8%
    423
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.26
    0.03
    30
    +0.14
    0.03
    61
    +0.11
    0.03
    Negative Logits
    emis
    -1.71
    styles
    -1.58
     franchise
    -1.57
     positions
    -1.54
    books
    -1.53
     coverage
    -1.53
    powered
    -1.52
     lives
    -1.51
    powers
    -1.50
     covers
    -1.50
    POSITIVE LOGITS
    thon
    1.94
    ¿½
    1.90
    1.73
    ↵↵
    1.73
     ↵
    1.73
    ↵
    1.73
    ↵  ³³³
    1.73
    č↵
    1.73
    1.73
    <|outofrange|>
    1.73
    Activations Density 0.154%

    No Known Activations