© 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. 8764
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles of people and places

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.28
    1.6%
    511
    +0.14
    0.8%
    477
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.28
    0.08
    31
    +0.14
    0.07
    285
    +0.13
    0.08
    Negative Logits
    ı
    -3.79
    ↵  âĢĥ
    -3.67
    -3.67
    -3.67
    č↵
    -3.67
    ↵↵
    -3.67
    <|outofrange|>
    -3.67
    -3.67
    č↵
    -3.67
    <|padding|>
    -3.67
    POSITIVE LOGITS
    chaft
    2.94
    mith
    2.94
    ki
    2.89
    ource
    2.83
    hire
    2.71
    hte
    2.69
    quare
    2.67
    burg
    2.66
    dorff
    2.65
    dale
    2.62
    Activations Density 0.618%

    No Known Activations