© 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 EvalsExportsAPI 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. 27751
    Prev
    Next
    INDEX
    Explanations

    introductory phrases and sentence structures that set context or conditions

    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
    23
    +0.17
    0.9%
    205
    +0.12
    0.6%
    422
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.17
    0.04
    166
    +0.12
    0.03
    23
    +0.11
    0.04
    Negative Logits
    ¥
    -1.83
    ľĵ
    -1.79
    Ļª
    -1.70
    ĺ
    -1.66
    ĥ½
    -1.64
    lane
    -1.55
    ibles
    -1.54
    ĨĴ
    -1.54
    ¾
    -1.51
    Į
    -1.50
    POSITIVE LOGITS
     exemplary
    1.74
     Majesty
    1.65
     embodiments
    1.63
     Patent
    1.50
    ket
    1.48
     xe
    1.45
    orously
    1.42
    uing
    1.39
    pping
    1.35
    fine
    1.34
    Activations Density 0.162%

    No Known Activations