© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8862
    Prev
    Next
    INDEX
    Explanations

    variations of the word "irresponsible."

    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
    132
    +0.15
    0.8%
    450
    +0.14
    0.8%
    480
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.02
    410
    +0.14
    0.03
    132
    +0.13
    0.03
    Negative Logits
    ering
    -2.09
    er
    -1.88
    ers
    -1.87
    ed
    -1.76
    velopment
    -1.73
     respect
    -1.72
     generation
    -1.69
    ered
    -1.65
     expect
    -1.61
    heimer
    -1.57
    POSITIVE LOGITS
    ¦
    2.79
    ½
    2.62
    ª
    2.54
    reducible
    2.51
    ichlet
    2.39
    ¡
    2.35
    Ń
    2.33
    Į
    2.29
    »
    2.29
    Ĵ
    2.26
    Activations Density 0.188%

    No Known Activations