© 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. 24899
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency in various 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
    156
    +0.25
    1.5%
    189
    +0.13
    0.8%
    232
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.25
    0.02
    189
    +0.13
    0.02
    306
    +0.12
    0.01
    Negative Logits
    mania
    -1.73
    rier
    -1.68
    jours
    -1.63
    lla
    -1.61
     married
    -1.58
    riber
    -1.58
     nationality
    -1.58
    ypse
    -1.55
    llll
    -1.54
    sell
    -1.51
    POSITIVE LOGITS
    Ŀ
    1.91
     efficiency
    1.76
    ļ
    1.75
    ¨
    1.68
    ķ
    1.64
    ously
    1.62
     accru
    1.62
     detection
    1.62
    Ł
    1.60
     efficiencies
    1.60
    Activations Density 0.068%

    No Known Activations