© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to programming and data manipulation

    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
    307
    +0.25
    1.5%
    311
    +0.12
    0.7%
    401
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.25
    0.04
    479
    +0.12
    0.03
    357
    +0.12
    0.04
    Negative Logits
    Ĭ
    -4.15
    »¿
    -4.00
    §
    -3.83
    ¨
    -3.76
    ł
    -3.71
    ĥ
    -3.67
    ¸
    -3.65
    Īĺ
    -3.64
    ľĵ
    -3.62
    Į
    -3.61
    POSITIVE LOGITS
     consisting
    2.14
     like
    2.09
     analyzer
    2.08
     called
    2.03
     named
    2.00
     somewhere
    1.99
     whose
    1.96
     instance
    1.95
    holder
    1.92
     object
    1.86
    Activations Density 0.317%

    No Known Activations