© 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. 27850
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to genetics and chromosomes

    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
    369
    +0.12
    0.7%
    352
    +0.12
    0.6%
    62
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.12
    0.11
    487
    +0.12
    0.06
    322
    +0.11
    0.06
    Negative Logits
    anges
    -1.66
    .";
    -1.65
    ";
    -1.63
     ways
    -1.48
    mable
    -1.40
     ();
    -1.37
     Quinn
    -1.32
    ported
    -1.31
    ?”
    -1.29
    iences
    -1.27
    POSITIVE LOGITS
    ]{})
    1.84
    )~
    1.77
    ).)
    1.72
    `,`
    1.67
    ὶ
    1.58
    )',
    1.55
    à±į
    1.54
    `)
    1.52
    ://
    1.50
    )),
    1.50
    Activations Density 1.543%

    No Known Activations