© 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. 2-RES-SM
    11. 26220
    Prev
    Next
    INDEX
    Explanations

    queries and requests for information or action

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    419
    +0.17
    0.9%
    369
    +0.14
    0.8%
    263
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.17
    0.07
    158
    +0.14
    0.07
    263
    +0.11
    0.08
    Negative Logits
    Ļª
    -1.94
    iana
    -1.73
     itself
    -1.71
    į
    -1.66
    itarian
    -1.65
    terday
    -1.63
    ı
    -1.60
    ¾
    -1.57
    obal
    -1.56
    ¼
    -1.55
    POSITIVE LOGITS
     permission
    1.87
     publication
    1.68
     question
    1.62
    gmail
    1.54
     clarification
    1.54
     contact
    1.53
     asking
    1.50
     pardon
    1.50
     documentation
    1.48
     inclusion
    1.48
    Activations Density 1.126%

    No Known Activations