© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 28522
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions or inquiries for clarification

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    478
    +0.14
    0.8%
    5
    +0.14
    0.7%
    316
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.14
    0.02
    8
    +0.14
    0.01
    466
    +0.11
    0.02
    Negative Logits
    manship
    -2.14
    iances
    -1.95
    nikov
    -1.79
    arts
    -1.76
    ies
    -1.72
    ivities
    -1.70
    iance
    -1.68
    bows
    -1.67
    ict
    -1.65
    herin
    -1.63
    POSITIVE LOGITS
     "!"
    1.86
     Secondly
    1.60
    Į
    1.59
    quo
    1.55
    qc
    1.51
    ooo
    1.47
    ½
    1.46
     YES
    1.42
    ??
    1.42
    ī
    1.40
    Activations Density 0.058%

    No Known Activations