© 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. 4-RES-SM
    11. 9703
    Prev
    Next
    INDEX
    Explanations

    various elements related to programming and code execution

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.22
    1.3%
    365
    +0.14
    0.8%
    397
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.22
    0.04
    354
    +0.14
    0.06
    219
    +0.14
    0.06
    Negative Logits
    .”
    -2.03
    Ļª
    -2.01
    .’”
    -1.87
    ”;
    -1.85
    .“
    -1.81
    .”).
    -1.78
    .^\[[@
    -1.77
    ].)
    -1.76
    ,”
    -1.74
    ]{}.
    -1.74
    POSITIVE LOGITS
     disappears
    2.38
     appears
    2.34
     doesn
    2.34
     contains
    2.33
     seems
    2.32
     behaves
    2.23
     won
    2.23
     should
    2.17
     doesnt
    2.16
     goes
    2.14
    Activations Density 0.472%

    No Known Activations