© 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. 1-RES-SM
    11. 29633
    Prev
    Next
    INDEX
    Explanations

    words related to health and medical conditions

    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
    111
    +0.20
    1.2%
    410
    +0.18
    1.1%
    113
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.20
    0.02
    410
    +0.18
    0.03
    64
    +0.12
    0.02
    Negative Logits
    ";
    -1.45
    ogue
    -1.39
     };
    -1.39
     matter
    -1.38
    ington
    -1.36
     sectional
    -1.35
    ropolitan
    -1.34
    ';
    -1.33
    inos
    -1.31
     Southern
    -1.31
    POSITIVE LOGITS
    ии
    1.85
    à°¿
    1.83
    нÑĭй
    1.79
    ик
    1.76
    еÑģк
    1.76
    иÑı
    1.75
    ÑĤе
    1.75
    ноÑģÑĤ
    1.75
    иÑĩеÑģк
    1.71
    ¥
    1.71
    Activations Density 0.087%

    No Known Activations