© 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. 32301
    Prev
    Next
    INDEX
    Explanations

    specific references to members, entities, or components within a structured context or argument

    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
    244
    +0.15
    0.8%
    447
    +0.13
    0.7%
    403
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.15
    0.07
    14
    +0.13
    0.08
    403
    +0.13
    0.06
    Negative Logits
    rVert
    -1.60
     emphasis
    -1.55
     oxygen
    -1.48
     Drain
    -1.46
     priority
    -1.42
    oddsidemargin
    -1.36
     truth
    -1.35
    liness
    -1.32
     smoke
    -1.30
     premium
    -1.29
    POSITIVE LOGITS
     ↵
    3.27
    3.27
              ↵
    3.27
    ↵
    3.27
    ↵
    3.27
    ↵  âĢĥ
    3.27
    ↵
    3.27
    ↵
    3.27
    č↵
    3.27
      ↵
    3.27
    Activations Density 0.676%

    No Known Activations