© 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. 26129
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses in text

    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
    188
    +0.17
    1.0%
    478
    +0.17
    1.0%
    350
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.17
    0.04
    350
    +0.17
    0.02
    157
    +0.13
    0.03
    Negative Logits
     than
    -1.43
    []{
    -1.43
     wherever
    -1.40
    ]{};
    -1.36
    inator
    -1.35
     bedside
    -1.33
     highlight
    -1.31
     diagnosis
    -1.31
     controls
    -1.31
    elines
    -1.29
    POSITIVE LOGITS
     ),
    1.66
    >=
    1.62
    distributed
    1.53
    )$-
    1.49
    INCLUDING
    1.49
    doibase
    1.48
    legal
    1.47
     gonna
    1.41
    hereinafter
    1.33
     copyrighted
    1.33
    Activations Density 0.082%

    No Known Activations