© 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. 23811
    Prev
    Next
    INDEX
    Explanations

    terms related to professional status or activities

    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
    377
    +0.12
    0.6%
    283
    +0.11
    0.6%
    124
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.12
    0.02
    377
    +0.11
    0.02
    218
    +0.11
    0.02
    Negative Logits
    ETHOD
    -1.61
    inate
    -1.55
    ARGET
    -1.50
    ance
    -1.47
     favor
    -1.47
     AFFIRMED
    -1.43
    izumab
    -1.42
    ibular
    -1.42
    ingle
    -1.42
    ocardi
    -1.40
    POSITIVE LOGITS
    clamation
    1.91
    claimer
    1.78
    ī
    1.74
    claim
    1.72
    jek
    1.61
    sci
    1.52
    ceeding
    1.52
     legend
    1.47
     auction
    1.46
    ph
    1.45
    Activations Density 0.041%

    No Known Activations