© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    references to respiratory health conditions and related medical terms

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.1%
    468
    +0.14
    0.8%
    503
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.18
    0.01
    503
    +0.14
    0.01
    13
    +0.12
    0.01
    Negative Logits
    agers
    -1.60
     '</
    -1.57
    glich
    -1.57
    eter
    -1.54
    usterity
    -1.53
     dire
    -1.50
    oe
    -1.47
    '));
    -1.47
    yla
    -1.46
    eting
    -1.43
    POSITIVE LOGITS
     cavity
    1.84
    ists
    1.52
    shire
    1.51
     clearance
    1.50
    anne
    1.49
    àµį
    1.47
    writers
    1.46
    s
    1.46
    ist
    1.40
    ients
    1.39
    Activations Density 0.048%

    No Known Activations