© 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. 29896
    Prev
    Next
    INDEX
    Explanations

    references to anti-LGBTQ political organizations and related topics

    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
    412
    +0.16
    0.9%
    369
    +0.13
    0.7%
    331
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.16
    0.03
    508
    +0.13
    0.02
    67
    +0.11
    0.02
    Negative Logits
     simplicity
    -1.54
     QC
    -1.52
     ages
    -1.46
     thought
    -1.43
     owe
    -1.43
     hereby
    -1.41
     fois
    -1.40
    isse
    -1.40
     uniformity
    -1.39
     corner
    -1.38
    POSITIVE LOGITS
    ondo
    1.73
    atar
    1.68
    ientos
    1.63
    ira
    1.57
    horn
    1.57
    vist
    1.56
    ño
    1.55
    naire
    1.53
    uez
    1.52
    hetti
    1.50
    Activations Density 0.048%

    No Known Activations