© 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. 13610
    Prev
    Next
    INDEX
    Explanations

    questions related to quantity, duration, and effort

    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
    346
    +0.15
    0.8%
    174
    +0.12
    0.7%
    453
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.15
    0.04
    7
    +0.12
    0.01
    267
    +0.12
    0.03
    Negative Logits
    ment
    -1.91
    ments
    -1.88
    mentation
    -1.68
    matically
    -1.58
    ivity
    -1.51
    ively
    -1.47
    ing
    -1.45
     intention
    -1.45
    front
    -1.43
    merce
    -1.38
    POSITIVE LOGITS
    Ĭ
    3.15
    ĺ
    3.07
    Ļª
    2.94
    ł
    2.87
    ĥ½
    2.75
    ĸ´
    2.72
    ¡
    2.70
    ¸
    2.69
    º
    2.68
    ľĵ
    2.61
    Activations Density 0.268%

    No Known Activations