© 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. 8781
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations or landmarks

    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
    156
    +0.34
    2.2%
    21
    +0.23
    1.4%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.34
    0.04
    156
    +0.23
    0.12
    134
    +0.12
    0.11
    Negative Logits
     ↵
    -3.45
    ↵
    -3.45
    ↵
    -3.45
    <|outofrange|>
    -3.45
    ↵
    -3.45
     ↵
    -3.45
    <|outofrange|>
    -3.45
    ↵
    -3.45
    -3.45
    ↵
    -3.45
    POSITIVE LOGITS
     Awards
    1.70
    ypse
    1.70
    ale
    1.66
     Award
    1.58
     Studios
    1.58
    ossa
    1.58
     Entertainment
    1.57
    asters
    1.57
     Tours
    1.54
     Trophy
    1.54
    Activations Density 1.405%

    No Known Activations