© 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. 28464
    Prev
    Next
    INDEX
    Explanations

    instances of code keywords related to static and virtual declarations

    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
    494
    +0.14
    0.8%
    45
    +0.12
    0.7%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.14
    0.02
    494
    +0.12
    0.02
    486
    +0.12
    0.02
    Negative Logits
    zzo
    -1.67
    ĸ´
    -1.66
    ppen
    -1.63
    zione
    -1.63
    ŀ
    -1.53
    ·¸
    -1.53
    ľĵ
    -1.48
    zzi
    -1.48
     eligible
    -1.46
    Ķ
    -1.46
    POSITIVE LOGITS
    fiddle
    1.69
     inspiration
    1.66
    ize
    1.58
     blows
    1.58
     inline
    1.52
    ök
    1.50
    ://
    1.49
     cents
    1.49
    uary
    1.45
     shelves
    1.42
    Activations Density 0.062%

    No Known Activations