© 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. 25505
    Prev
    Next
    INDEX
    Explanations

    words associated with medical conditions and illnesses related to the sinuses

    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
    182
    +0.15
    0.9%
    156
    +0.11
    0.7%
    448
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.15
    0.01
    71
    +0.11
    0.02
    321
    +0.11
    0.01
    Negative Logits
     promise
    -1.70
      ↵
    -1.52
     shame
    -1.52
     behalf
    -1.50
     careful
    -1.50
     interest
    -1.49
    bbe
    -1.49
     damned
    -1.48
     yer
    -1.47
     honour
    -1.46
    POSITIVE LOGITS
    oidal
    2.23
    bol
    1.94
    illo
    1.86
    àµį
    1.80
    heimer
    1.76
    arios
    1.72
    oids
    1.70
    atics
    1.68
    itis
    1.68
    ophone
    1.67
    Activations Density 0.052%

    No Known Activations