© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    references to serious health conditions, particularly cardiovascular-related issues

    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
    366
    +0.14
    0.8%
    30
    +0.13
    0.7%
    408
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.14
    0.01
    216
    +0.13
    0.05
    510
    +0.11
    0.05
    Negative Logits
     Ale
    -2.11
     Kurdish
    -2.08
     hops
    -2.04
     Django
    -2.02
     SEO
    -2.01
     cookie
    -2.01
     cookies
    -2.00
     Penguin
    -2.00
     Assad
    -1.99
     Somal
    -1.89
    POSITIVE LOGITS
    ĻĤ
    3.94
     ventricular
    3.58
     myocardium
    3.54
     myocardial
    3.53
     cardiac
    3.52
     myocard
    3.51
    ij
    3.49
     cardiomy
    3.46
     arrhythm
    3.42
     ECG
    3.38
    Activations Density 0.596%

    No Known Activations