© 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. 15095
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly prime factors and mathematical expressions

    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
    21
    +0.16
    0.9%
    81
    +0.15
    0.9%
    78
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.16
    0.01
    142
    +0.15
    0.01
    482
    +0.14
    0.01
    Negative Logits
    .^[@
    -1.51
     slack
    -1.47
     copy
    -1.41
    ";
    -1.31
    compare
    -1.29
     enough
    -1.29
     {};
    -1.29
     same
    -1.28
     speedy
    -1.26
    gers
    -1.26
    POSITIVE LOGITS
     ».
    1.63
    ...](
    1.59
     »,
    1.54
    ?’
    1.52
     """
    1.52
    ’,
    1.51
     »
    1.50
    urname
    1.49
    ’.
    1.49
    .’
    1.45
    Activations Density 0.044%

    No Known Activations