© 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. 23966
    Prev
    Next
    INDEX
    Explanations

    references to scanning processes and scanning equipment

    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
    156
    +0.26
    1.5%
    490
    +0.12
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.26
    0.01
    131
    +0.12
    0.01
    230
    +0.12
    0.01
    Negative Logits
     particular
    -1.68
     careful
    -1.54
     generality
    -1.50
     appreciate
    -1.48
     importance
    -1.47
    §
    -1.47
    ĥ½
    -1.41
    rely
    -1.41
    estly
    -1.34
     Columb
    -1.30
    POSITIVE LOGITS
    list
    1.75
    lon
    1.65
    nor
    1.63
    avage
    1.60
    neck
    1.58
    dv
    1.56
    ty
    1.56
    buck
    1.52
    idine
    1.50
    bot
    1.49
    Activations Density 0.063%

    No Known Activations