© 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. 24024
    Prev
    Next
    INDEX
    Explanations

    terminology related to manufacturing and synthesis processes

    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
    +0.15
    0.8%
    173
    +0.14
    0.8%
    360
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.15
    0.01
    276
    +0.14
    0.01
    48
    +0.12
    0.01
    Negative Logits
    ĥ½
    -1.75
    lessly
    -1.54
    course
    -1.42
    join
    -1.42
    race
    -1.39
    anza
    -1.37
    ys
    -1.35
    Ļª
    -1.35
    wic
    -1.33
    ished
    -1.31
    POSITIVE LOGITS
     by
    1.67
     ones
    1.40
     inexpensive
    1.35
     synthesis
    1.34
     accordingly
    1.34
     precursors
    1.34
     these
    1.33
     Acting
    1.31
    cription
    1.31
     therefrom
    1.30
    Activations Density 0.072%

    No Known Activations