© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11429
    Prev
    Next
    INDEX
    Explanations

    references to biblical scripture and quotations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.12
    0.7%
    206
    +0.12
    0.6%
    434
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.12
    0.00
    460
    +0.12
    0.03
    206
    +0.11
    0.07
    Negative Logits
    ľĵ
    -3.04
    ¿½
    -2.80
    ķ
    -2.61
    ĥ½
    -2.53
    ¨
    -2.40
    ī
    -2.37
    Ħ
    -2.36
    ģ
    -2.35
    ħ
    -2.32
    Ĥ
    -2.30
    POSITIVE LOGITS
     verse
    2.48
     paragraph
    2.21
     Chapter
    2.16
    paragraph
    2.11
     Appendix
    2.03
     quoted
    2.00
     chapter
    1.99
    vii
    1.94
    )):
    1.89
    unnumbered
    1.89
    Activations Density 1.626%

    No Known Activations