© 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. Residuals
    9. 2-RES-SM
    11. 27055
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and healthcare

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    320
    +0.17
    1.0%
    47
    +0.16
    0.9%
    487
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.17
    0.04
    320
    +0.16
    0.07
    436
    +0.15
    0.04
    Negative Logits
    ()));
    -2.07
    "));
    -1.66
    '));
    -1.54
    ));
    -1.52
    )\].
    -1.48
    ).)
    -1.46
     also
    -1.46
    nbsp
    -1.45
     titled
    -1.44
    )\]
    -1.43
    POSITIVE LOGITS
     or
    2.02
     nor
    1.97
     and
    1.89
     AND
    1.78
     versus
    1.63
    -,
    1.61
    enders
    1.50
    iera
    1.49
    inous
    1.44
    ouses
    1.43
    Activations Density 1.747%

    No Known Activations