© 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. 24247
    Prev
    Next
    INDEX
    Explanations

    topics related to health, specifically illnesses and their impacts

    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
    23
    +0.14
    0.8%
    450
    +0.12
    0.7%
    344
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.14
    0.13
    148
    +0.12
    0.07
    46
    +0.12
    0.07
    Negative Logits
     sheets
    -1.73
    heets
    -1.61
    fonts
    -1.47
    "){
    -1.41
    uary
    -1.40
    =#
    -1.40
     Letter
    -1.40
     Sheets
    -1.40
     Measurements
    -1.39
    nez
    -1.38
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.59
     evolutionary
    1.56
    coming
    1.51
    tering
    1.50
     ferment
    1.47
     unravel
    1.43
     economic
    1.38
     adversarial
    1.37
     politic
    1.35
     doctr
    1.34
    Activations Density 3.451%

    No Known Activations