© 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. 28602
    Prev
    Next
    INDEX
    Explanations

    terms related to dental health and care

    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
    +0.20
    1.2%
    71
    +0.17
    1.1%
    173
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.20
    0.02
    71
    +0.17
    0.02
    466
    +0.17
    0.01
    Negative Logits
    ı
    -2.60
    Ī
    -2.51
    Ŀ
    -2.48
    -2.41
    <|outofrange|>
    -2.41
    -2.41
    -2.41
    č↵č↵
    -2.41
    č↵
    -2.41
          ↵
    -2.41
    POSITIVE LOGITS
    caster
    1.80
    wikipedia
    1.63
    acia
    1.61
    makers
    1.60
     needs
    1.58
    sworth
    1.57
    worth
    1.56
    hurst
    1.50
    apple
    1.50
    \$
    1.48
    Activations Density 0.054%

    No Known Activations