© 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. 32178
    Prev
    Next
    INDEX
    Explanations

    HTML and code snippets related to programming and web development

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.30
    1.7%
    159
    +0.12
    0.7%
    322
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.30
    0.02
    379
    +0.12
    0.04
    159
    +0.10
    0.03
    Negative Logits
    )\]
    -1.89
     respectively
    -1.82
    )\].
    -1.75
     deference
    -1.51
     \[
    -1.50
     exception
    -1.48
     epochs
    -1.43
     corresponding
    -1.42
    apter
    -1.34
     redeem
    -1.33
    POSITIVE LOGITS
    Īĺ
    1.91
    ¡
    1.82
    Ĵ
    1.82
    į
    1.81
    ¢
    1.78
    ĻĤ
    1.72
    Ģ
    1.68
    §
    1.68
    Ļª
    1.67
      ↵
    1.65
    Activations Density 0.186%

    No Known Activations