© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28638
    Prev
    Next
    INDEX
    Explanations

    present tense forms of the verb "to be."

    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
    23
    +0.42
    2.6%
    478
    +0.15
    0.9%
    84
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.42
    0.16
    337
    +0.15
    0.11
    8
    +0.11
    0.08
    Negative Logits
    »¿
    -3.89
    ¢
    -3.59
    §
    -3.52
    ¥
    -3.46
    ¼
    -3.44
    Ŀ
    -3.36
    Ľ
    -3.29
    ª
    -3.28
    ł
    -3.19
    ©
    -3.16
    POSITIVE LOGITS
     CAG
    1.82
     widespread
    1.78
     unanimous
    1.77
    opropyl
    1.77
     overwhelming
    1.72
     detailed
    1.70
     simplicity
    1.62
     extensive
    1.60
     ammonium
    1.55
     jelly
    1.54
    Activations Density 1.496%

    No Known Activations