© 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. 30862
    Prev
    Next
    INDEX
    Explanations

    function and variable declarations in programming 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
    17
    +0.16
    0.9%
    482
    +0.16
    0.9%
    187
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.16
    0.05
    482
    +0.16
    0.10
    322
    +0.14
    0.04
    Negative Logits
     hereby
    -1.60
    ĥ½
    -1.48
    ¿½
    -1.38
    cing
    -1.36
    will
    -1.33
    gg
    -1.32
     authors
    -1.31
     Elect
    -1.26
    these
    -1.26
     culture
    -1.25
    POSITIVE LOGITS
     <-
    1.79
    iculously
    1.50
    ariate
    1.48
    minist
    1.43
    àµ
    1.40
    àµį
    1.40
    header
    1.40
    Ļª
    1.39
    à«ĩ
    1.37
    Handler
    1.36
    Activations Density 0.962%

    No Known Activations