© 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. 13135
    Prev
    Next
    INDEX
    Explanations

    references to God and divine concepts

    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
    156
    +0.17
    0.9%
    450
    +0.15
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.17
    0.04
    450
    +0.15
    0.03
    305
    +0.14
    0.02
    Negative Logits
    stituted
    -1.95
     cultures
    -1.79
     hereto
    -1.68
    clusions
    -1.62
    dll
    -1.56
    itzerland
    -1.54
    stitute
    -1.46
    dle
    -1.46
     pept
    -1.45
     supra
    -1.43
    POSITIVE LOGITS
    frey
    3.10
    dess
    2.54
     Himself
    2.25
    ship
    2.21
    father
    2.09
    zilla
    2.07
    fors
    2.00
    liness
    1.98
    damn
    1.89
     himself
    1.85
    Activations Density 0.249%

    No Known Activations