© 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. 29952
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating movement or direction

    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
    69
    +0.30
    1.8%
    478
    +0.17
    1.0%
    434
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.30
    0.23
    151
    +0.17
    0.09
    434
    +0.13
    0.09
    Negative Logits
    um
    -1.59
    while
    -1.50
    ario
    -1.50
    arro
    -1.47
    arity
    -1.47
    holes
    -1.46
    ário
    -1.44
    arch
    -1.41
    hole
    -1.41
    CPU
    -1.40
    POSITIVE LOGITS
    dden
    2.31
    pless
    2.19
    wing
    2.07
     be
    1.89
    dule
    1.88
    pping
    1.80
     herself
    1.79
     qualify
    1.75
    wed
    1.73
     accommodate
    1.72
    Activations Density 1.298%

    No Known Activations