© 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. 2-RES-SM
    11. 28014
    Prev
    Next
    INDEX
    Explanations

    instances of religious or spiritual concepts and teachings

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    268
    +0.16
    0.9%
    322
    +0.14
    0.8%
    205
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.16
    0.09
    56
    +0.14
    -0.03
    322
    +0.13
    -0.00
    Negative Logits
    ľĵ
    -2.22
    ³
    -2.04
    ¬
    -2.01
    Ļª
    -2.00
    -1.99
    ↵
    -1.99
    ↵
    -1.99
    ↵
    -1.99
    ↵
    -1.99
    -1.99
    POSITIVE LOGITS
     prayer
    3.02
     Prayer
    2.80
     Bible
    2.73
     prayers
    2.73
     Scripture
    2.67
     Jesus
    2.63
     sermon
    2.62
     Gospel
    2.58
     Divine
    2.56
     divine
    2.53
    Activations Density 2.771%

    No Known Activations