© 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. 28659
    Prev
    Next
    INDEX
    Explanations

    terms associated with religious or spiritual significance, particularly regarding the concept of holiness

    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
    369
    +0.12
    0.7%
    111
    +0.10
    0.6%
    317
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.12
    0.02
    385
    +0.10
    0.01
    268
    +0.10
    0.01
    Negative Logits
    yon
    -1.87
    onal
    -1.86
    ably
    -1.69
    able
    -1.60
    atal
    -1.58
    abel
    -1.58
     focusing
    -1.57
    ables
    -1.57
     pregnant
    -1.57
     planned
    -1.56
    POSITIVE LOGITS
    holds
    1.84
    borough
    1.78
    hold
    1.70
    eners
    1.70
    weather
    1.67
     Ages
    1.65
    holders
    1.60
     Telescope
    1.57
    riors
    1.56
     Trinity
    1.52
    Activations Density 0.148%

    No Known Activations