© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 28642
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and health topics

    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
    386
    +0.13
    0.8%
    2
    +0.13
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.04
    451
    +0.13
    0.03
    407
    +0.12
    0.03
    Negative Logits
    ¯
    -2.17
    Ŀ
    -2.13
    ´
    -2.10
    £
    -1.97
    ł
    -1.96
    µ
    -1.93
    ı
    -1.85
    ³
    -1.85
    °
    -1.85
    ķ
    -1.82
    POSITIVE LOGITS
    azine
    1.96
     insurance
    1.83
    sheet
    1.80
    liche
    1.70
     Insurance
    1.70
    igraphy
    1.69
    igraph
    1.62
     benefits
    1.61
    acia
    1.60
    risk
    1.60
    Activations Density 0.339%

    No Known Activations