© 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. 23858
    Prev
    Next
    INDEX
    Explanations

    instances of the word "usually" and its variations in context

    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
    +0.25
    1.4%
    87
    +0.14
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.25
    0.02
    398
    +0.14
    0.02
    87
    +0.12
    0.02
    Negative Logits
    Ĭ
    -3.08
    Ħ
    -3.08
    ®
    -2.97
    İ
    -2.96
    IJ
    -2.91
    Ĩ
    -2.70
    ĭ
    -2.69
    ±
    -2.69
    ļ
    -2.66
    §
    -2.61
    POSITIVE LOGITS
    chitz
    1.80
    ympt
    1.58
    cology
    1.56
    ering
    1.55
     prevail
    1.52
    ster
    1.52
    )|^
    1.49
     suffice
    1.49
    optera
    1.49
     encounter
    1.47
    Activations Density 0.054%

    No Known Activations