© 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. 23847
    Prev
    Next
    INDEX
    Explanations

    specific references to facilities or locations

    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
    +0.33
    2.0%
    478
    +0.15
    0.9%
    203
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.33
    0.18
    23
    +0.15
    0.15
    467
    +0.13
    0.10
    Negative Logits
    !,
    -1.80
    heets
    -1.74
    ,
    -1.72
    ++,
    -1.71
    vist
    -1.68
    ious
    -1.63
    ist
    -1.61
    joy
    -1.61
    imize
    -1.59
    aho
    -1.59
    POSITIVE LOGITS
    omitempty
    1.67
     sudden
    1.56
     '$
    1.55
     luck
    1.55
     particularly
    1.49
     slightest
    1.49
     beginning
    1.48
    possibly
    1.46
     systematic
    1.44
     indeed
    1.44
    Activations Density 1.819%

    No Known Activations