© 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. 29194
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "be" in various forms or contexts

    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
    +0.20
    1.1%
    404
    +0.11
    0.6%
    123
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.20
    0.06
    123
    +0.11
    0.06
    244
    +0.11
    0.06
    Negative Logits
    Ŀ
    -2.50
    Ī
    -2.49
    ¢
    -2.47
    ©
    -2.46
    ŀ
    -2.45
    ļ
    -2.40
    İ
    -2.40
    ł
    -2.32
    §
    -2.30
    ¡
    -2.23
    POSITIVE LOGITS
     anything
    1.73
    aucoup
    1.70
    quez
    1.60
     publicly
    1.55
     brib
    1.54
     nullptr
    1.51
     clinically
    1.49
     distributed
    1.48
    aded
    1.48
     accessed
    1.46
    Activations Density 0.299%

    No Known Activations