© 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. 2-RES-SM
    11. 27218
    Prev
    Next
    INDEX
    Explanations

    instances of the word "used" 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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.11
    0.6%
    485
    +0.11
    0.6%
    309
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.11
    0.03
    184
    +0.11
    0.02
    73
    +0.11
    0.02
    Negative Logits
    »¿
    -2.64
    Ļª
    -2.24
    ypse
    -2.15
    ĨĴ
    -2.02
    Ĩ
    -2.02
    ĻĤ
    -1.99
    à°¿
    -1.95
    ¿½
    -1.93
    Ī
    -1.91
    ¼
    -1.87
    POSITIVE LOGITS
     interchange
    1.91
     for
    1.83
     sparing
    1.75
     either
    1.64
     primarily
    1.61
     essentially
    1.58
     nowadays
    1.57
     only
    1.56
     to
    1.56
    okinetic
    1.56
    Activations Density 0.065%

    No Known Activations