© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show" and its variations

    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
    72
    +0.13
    0.7%
    211
    +0.11
    0.6%
    263
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.13
    0.03
    228
    +0.11
    0.02
    72
    +0.11
    0.03
    Negative Logits
    ambda
    -1.72
    ricular
    -1.62
    Aldrich
    -1.61
    Bay
    -1.59
    unnumbered
    -1.58
    bishop
    -1.54
    heim
    -1.54
    dule
    -1.52
    stein
    -1.52
    inux
    -1.51
    POSITIVE LOGITS
    cases
    2.39
    ered
    2.15
    ering
    2.14
     signs
    2.08
    case
    1.86
     positivity
    1.85
     kindness
    1.78
     solidarity
    1.75
     appreciation
    1.75
     respect
    1.69
    Activations Density 0.102%

    No Known Activations