© 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. 24453
    Prev
    Next
    INDEX
    Explanations

    terms related to medical screening processes

    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
    156
    +0.21
    1.2%
    281
    +0.12
    0.7%
    173
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.21
    0.01
    484
    +0.12
    0.02
    156
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.95
    §
    -2.73
    ½
    -2.53
    ĸ´
    -2.46
    ¾
    -2.38
    ŀ
    -2.37
    Į
    -2.35
    ©
    -2.28
    Ŀ
    -2.28
    Ľ
    -2.23
    POSITIVE LOGITS
    ton
    1.49
    haus
    1.48
     measures
    1.47
     indicator
    1.46
    ibrary
    1.44
    iew
    1.44
     selection
    1.41
    naire
    1.40
    osa
    1.40
    grams
    1.40
    Activations Density 0.090%

    No Known Activations