© 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. 29982
    Prev
    Next
    INDEX
    Explanations

    biological terms related to genetics and infectious diseases

    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
    156
    +0.22
    1.3%
    244
    +0.12
    0.7%
    81
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.22
    0.02
    184
    +0.12
    0.02
    425
    +0.10
    0.01
    Negative Logits
    ©
    -3.21
    ↵↵
    -3.12
    ↵↵
    -3.12
          ↵
    -3.12
    <|outofrange|>
    -3.12
    ↵
    -3.12
     ↵
    -3.12
    č↵
    -3.12
    <|outofrange|>
    -3.12
    -3.12
    POSITIVE LOGITS
    hell
    2.54
    creen
    2.05
    pace
    1.95
    ace
    1.66
    hoe
    1.65
    uit
    1.64
    weet
    1.63
    mith
    1.61
    cript
    1.60
    ource
    1.56
    Activations Density 0.063%

    No Known Activations