© 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. 26057
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and its applications in daily life

    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
    77
    +0.15
    0.9%
    466
    +0.15
    0.9%
    156
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.15
    0.02
    386
    +0.15
    0.01
    372
    +0.15
    0.02
    Negative Logits
    ypse
    -1.90
    watson
    -1.76
    ties
    -1.63
    ESULT
    -1.61
    ipal
    -1.58
    ly
    -1.54
    stitutional
    -1.51
    visibility
    -1.49
    thirds
    -1.49
    lique
    -1.48
    POSITIVE LOGITS
    chnology
    1.78
    asures
    1.73
    ½
    1.56
    rers
    1.51
     pains
    1.47
    aments
    1.46
    cks
    1.45
    achers
    1.43
     ups
    1.42
    amm
    1.39
    Activations Density 0.173%

    No Known Activations