© 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. 29839
    Prev
    Next
    INDEX
    Explanations

    comparative terms and expressions indicating quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    375
    +0.12
    0.7%
    338
    +0.12
    0.7%
    23
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.12
    0.06
    179
    +0.12
    0.06
    338
    +0.12
    0.07
    Negative Logits
    tees
    -1.95
    ¼
    -1.81
    endas
    -1.70
    ancel
    -1.70
    »
    -1.62
     begins
    -1.59
    clamation
    -1.57
     thereon
    -1.51
    ees
    -1.51
    tee
    -1.49
    POSITIVE LOGITS
     than
    1.85
     expensive
    1.66
    )$-
    1.63
    efficient
    1.56
    chitz
    1.54
     heterogeneous
    1.54
     coincidence
    1.54
    aned
    1.54
    expensive
    1.49
    quare
    1.49
    Activations Density 0.324%

    No Known Activations