© 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. 8539
    Prev
    Next
    INDEX
    Explanations

    terms related to orthopedic conditions and injuries, specifically involving joints and ligaments

    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
    153
    +0.15
    0.9%
    325
    +0.13
    0.7%
    179
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.15
    0.04
    325
    +0.13
    0.08
    216
    +0.12
    0.08
    Negative Logits
     Violet
    -1.97
     brew
    -1.90
     boil
    -1.82
     vap
    -1.82
     poison
    -1.80
     Starbucks
    -1.75
     recipes
    -1.72
     vapor
    -1.72
     poll
    -1.72
     messaging
    -1.72
    POSITIVE LOGITS
     knee
    3.26
     cartilage
    3.26
     tendon
    3.23
     ligament
    3.18
     tibial
    3.15
     flexion
    3.04
     ankle
    3.00
     joints
    2.95
    ł
    2.74
     deform
    2.71
    Activations Density 1.053%

    No Known Activations