© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to medical conditions and treatments

    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
    98
    +0.16
    0.9%
    466
    +0.11
    0.6%
    158
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.16
    0.03
    48
    +0.11
    0.03
    300
    +0.11
    0.03
    Negative Logits
     done
    -1.77
     recall
    -1.68
     exact
    -1.58
     politic
    -1.53
     date
    -1.49
     different
    -1.47
     concerned
    -1.46
     sid
    -1.43
     positive
    -1.42
     normal
    -1.42
    POSITIVE LOGITS
    ¢
    3.76
    ĸ
    3.50
    ¤
    3.46
    Ł
    3.45
    »¿
    3.42
    Ń
    3.36
    ĩ
    3.30
    Ĺ
    3.29
    IJ
    3.28
    £
    3.26
    Activations Density 0.164%

    No Known Activations