© 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. 25010
    Prev
    Next
    INDEX
    Explanations

    instances of the word "continue" and its variations

    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
    435
    +0.11
    0.6%
    464
    +0.11
    0.6%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.11
    0.04
    435
    +0.11
    0.03
    68
    +0.11
    0.04
    Negative Logits
    ĨĴ
    -3.40
    ģ
    -3.28
    ½
    -3.21
    Ģ
    -2.83
    ĺ
    -2.78
    į
    -2.76
    ĩ
    -2.68
    ¬
    -2.68
    ŀ
    -2.67
    Ī
    -2.65
    POSITIVE LOGITS
     "@
    1.45
    forth
    1.43
     WARRANTY
    1.39
    initis
    1.38
     veget
    1.35
    >>>
    1.35
     READ
    1.34
    reign
    1.34
     './
    1.32
    cing
    1.31
    Activations Density 0.100%

    No Known Activations