© 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. 26231
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those relating to time or duration

    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
    46
    +0.15
    0.9%
    477
    +0.15
    0.9%
    396
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.15
    0.06
    458
    +0.15
    0.04
    307
    +0.14
    0.05
    Negative Logits
    ellar
    -1.45
     mistake
    -1.40
     preponderance
    -1.38
    SYMBOL
    -1.36
    Syntax
    -1.34
    ATIONAL
    -1.33
    NOTES
    -1.32
     exchange
    -1.31
     importance
    -1.31
     Circuit
    -1.29
    POSITIVE LOGITS
    izumab
    1.92
    ¶
    1.86
    ingly
    1.81
    º
    1.78
    teenth
    1.74
    itud
    1.74
    esian
    1.68
    leys
    1.66
    hours
    1.55
    :`
    1.54
    Activations Density 0.305%

    No Known Activations