© 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. 2-RES-SM
    11. 26060
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to beauty and personal care

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.17
    1.0%
    111
    +0.15
    0.9%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.17
    0.09
    129
    +0.15
    0.02
    53
    +0.13
    0.09
    Negative Logits
     aid
    -1.48
    "}](#
    -1.45
    ).)
    -1.44
    path
    -1.42
    ystems
    -1.41
     DOI
    -1.40
    ).\
    -1.40
    uelle
    -1.38
     governing
    -1.37
    ural
    -1.37
    POSITIVE LOGITS
    ¼
    2.03
    Į
    1.74
    Ī
    1.74
    ½
    1.67
    References
    1.53
    About
    1.51
     moon
    1.49
    then
    1.46
    woke
    1.44
    ŀ
    1.44
    Activations Density 0.775%

    No Known Activations