© 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. 1-RES-SM
    11. 30153
    Prev
    Next
    INDEX
    Explanations

    references to places and proper nouns

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    337
    +0.12
    0.7%
    135
    +0.12
    0.7%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.12
    0.05
    337
    +0.12
    0.08
    445
    +0.10
    0.05
    Negative Logits
    eous
    -1.69
    keit
    -1.67
    rceil
    -1.57
     agg
    -1.55
     ")
    -1.55
    hift
    -1.55
    undo
    -1.47
    acency
    -1.47
    lessly
    -1.46
     repetitive
    -1.45
    POSITIVE LOGITS
    ↵↵
    4.08
    č↵
    4.08
    ↵
    4.08
    4.08
    ↵
    4.08
    <|outofrange|>
    4.08
    <|outofrange|>
    4.08
    4.08
    ↵
    4.08
    ↵
    4.08
    Activations Density 2.449%

    No Known Activations