© 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. 29912
    Prev
    Next
    INDEX
    Explanations

    concepts related to significant social issues and emotional experiences

    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
    1
    +0.13
    0.7%
    332
    +0.12
    0.6%
    410
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.01
    338
    +0.12
    0.01
    84
    +0.10
    0.00
    Negative Logits
    Ļ
    -2.12
    ħ
    -2.08
    ģ
    -2.03
    į
    -1.89
    ±
    -1.83
    Ł
    -1.82
    ¥
    -1.78
    Ī
    -1.77
    ³
    -1.73
    º
    -1.70
    POSITIVE LOGITS
    osevelt
    1.56
    illard
    1.55
     fn
    1.48
    ijan
    1.41
    GREEK
    1.40
     Suzuki
    1.39
    eries
    1.38
    itions
    1.36
     necrosis
    1.34
    iley
    1.31
    Activations Density 0.002%

    No Known Activations