© 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. 4-RES-SM
    11. 11923
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until."

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.15
    0.8%
    466
    +0.13
    0.8%
    213
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.15
    0.04
    106
    +0.13
    0.03
    449
    +0.10
    0.03
    Negative Logits
    ¢
    -3.13
    Ľ
    -2.89
    ħ
    -2.81
    ¡
    -2.78
    »¿
    -2.73
    į
    -2.72
    Ŀ
    -2.70
    ©
    -2.67
    ŀ
    -2.66
    İ
    -2.63
    POSITIVE LOGITS
    after
    1.89
     midnight
    1.80
     dawn
    1.76
     completion
    1.71
     they
    1.70
     adulthood
    1.64
     now
    1.64
    market
    1.58
     September
    1.57
     maturity
    1.56
    Activations Density 0.188%

    No Known Activations