© 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. 23846
    Prev
    Next
    INDEX
    Explanations

    phrases referencing a sense of history or lineage

    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
    23
    +0.14
    0.7%
    156
    +0.13
    0.7%
    459
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.04
    457
    +0.13
    0.04
    119
    +0.12
    0.02
    Negative Logits
     capable
    -1.70
    uncher
    -1.70
    eted
    -1.67
    selector
    -1.61
     hull
    -1.58
    headed
    -1.57
    ails
    -1.52
    blem
    -1.51
    bent
    -1.49
     rebounds
    -1.49
    POSITIVE LOGITS
    asia
    1.70
    hang
    1.58
    ansas
    1.54
    ubot
    1.47
     affairs
    1.46
    pec
    1.46
    otle
    1.46
    olid
    1.44
    fections
    1.42
     peoples
    1.41
    Activations Density 0.468%

    No Known Activations