© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24096
    Prev
    Next
    INDEX
    Explanations

    terms related to dental conditions and health issues

    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%
    164
    +0.13
    0.7%
    448
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    413
    +0.20
    0.01
    448
    +0.13
    0.01
    188
    +0.11
    0.01
    Negative Logits
    ¿
    -3.15
    ĨĴ
    -3.02
    ½
    -2.95
    ±
    -2.86
    ¾
    -2.81
    ª
    -2.76
    ³
    -2.72
    ĸ
    -2.71
    ķ
    -2.67
    ·
    -2.61
    POSITIVE LOGITS
    ulent
    1.92
    "}](#
    1.75
    less
    1.71
    iform
    1.71
    mage
    1.64
    ystems
    1.61
    illar
    1.60
    illon
    1.60
    iller
    1.59
    ENTIAL
    1.59
    Activations Density 0.078%

    No Known Activations