© 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. 1-RES-SM
    11. 30108
    Prev
    Next
    INDEX
    Explanations

    information related to health guidelines and fitness recommendations for adolescents

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.14
    0.8%
    337
    +0.13
    0.7%
    312
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    400
    +0.14
    0.03
    32
    +0.13
    0.05
    282
    +0.13
    0.05
    Negative Logits
     geneal
    -1.82
     Directory
    -1.81
    ª
    -1.73
    ´
    -1.71
    ľĵ
    -1.70
    ²
    -1.70
     Commons
    -1.70
    ĵ
    -1.64
    Ķ
    -1.62
     confidential
    -1.60
    POSITIVE LOGITS
     workout
    2.16
    weight
    2.00
     athlete
    1.95
    Fit
    1.90
     meditation
    1.88
     yoga
    1.87
    stress
    1.81
    otherap
    1.76
     Yoga
    1.75
    BMI
    1.69
    Activations Density 1.733%

    No Known Activations