© 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. 4-RES-SM
    11. 15240
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to hormones and endocrine factors

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    348
    +0.21
    1.2%
    442
    +0.14
    0.8%
    1
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.21
    0.03
    432
    +0.14
    0.03
    287
    +0.13
    0.03
    Negative Logits
    Ļª
    -1.84
    ®
    -1.52
     wifi
    -1.52
     corners
    -1.51
     finance
    -1.47
    ½
    -1.46
    issors
    -1.43
    piece
    -1.41
    ioni
    -1.40
     Euclidean
    -1.39
    POSITIVE LOGITS
    ergic
    2.63
     receptors
    2.56
     receptor
    2.41
     biosynthesis
    2.28
     secretion
    2.17
    receptor
    2.08
     agonists
    2.07
     secreted
    2.05
     antagonists
    2.04
     analogs
    2.01
    Activations Density 0.076%

    No Known Activations