© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and function definitions

    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
    156
    +0.33
    2.2%
    348
    +0.25
    1.7%
    466
    +0.23
    1.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.33
    -0.02
    9
    +0.25
    0.11
    17
    +0.23
    0.09
    Negative Logits
     regards
    -1.41
    wordpress
    -1.33
     undergraduate
    -1.26
     models
    -1.24
     horizon
    -1.24
    roads
    -1.24
     personnel
    -1.23
    castle
    -1.23
     expenditure
    -1.19
     namely
    -1.16
    POSITIVE LOGITS
    Ļª
    4.64
    ĭ
    4.29
    ´
    4.24
    Īĺ
    4.22
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    4.19
      ↵
    4.17
    į
    4.16
    ↵↵
    4.16
    4.16
    4.16
    Activations Density 3.265%

    No Known Activations