© 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. 24011
    Prev
    Next
    INDEX
    Explanations

    terms related to Asian identities and representation

    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
    156
    +0.22
    1.3%
    492
    +0.15
    0.9%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.22
    0.02
    424
    +0.15
    0.02
    421
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.21
    Ī
    -2.01
    ĥ
    -1.99
    Ļ
    -1.98
    ij
    -1.93
    Ģ
    -1.92
    -1.91
    <|outofrange|>
    -1.91
     ↵
    -1.91
    ↵
    -1.91
    POSITIVE LOGITS
     Affairs
    1.83
    iewicz
    1.82
    fan
    1.67
    istic
    1.65
    Net
    1.64
    ÃŃa
    1.64
    istan
    1.63
    Äĥ
    1.63
    asian
    1.60
    ism
    1.60
    Activations Density 0.042%

    No Known Activations