© 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. 13673
    Prev
    Next
    INDEX
    Explanations

    code components related to user interface elements and their interactions

    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
    75
    +0.14
    0.8%
    59
    +0.14
    0.8%
    106
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.14
    0.06
    47
    +0.14
    0.07
    75
    +0.12
    0.02
    Negative Logits
     anaerobic
    -1.75
     lactate
    -1.71
     ETH
    -1.70
     hydrolysis
    -1.68
     sludge
    -1.66
     amyl
    -1.62
     Brandon
    -1.60
    ({{\
    -1.57
     ester
    -1.55
     commodities
    -1.55
    POSITIVE LOGITS
    ĨĴ
    3.54
     Window
    3.46
     window
    3.10
    Ļª
    2.99
    Window
    2.92
    ±
    2.90
    ŀ
    2.76
     windows
    2.74
     dialog
    2.72
     popup
    2.62
    Activations Density 1.611%

    No Known Activations