© 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. 30079
    Prev
    Next
    INDEX
    Explanations

    references to required dependencies and modules in coding contexts

    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
    146
    +0.11
    0.6%
    51
    +0.10
    0.6%
    189
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.11
    0.03
    189
    +0.10
    0.01
    168
    +0.10
    0.01
    Negative Logits
     yards
    -1.64
     portion
    -1.44
    áĢº
    -1.42
    ocytes
    -1.41
    cells
    -1.35
    ...](
    -1.35
     cells
    -1.35
    .]
    -1.34
    ENRON
    -1.34
    ytes
    -1.30
    POSITIVE LOGITS
    orate
    1.69
    oses
    1.64
    ibilities
    1.63
     vet
    1.54
    openssl
    1.52
     withstand
    1.45
    forge
    1.45
     pardon
    1.43
    ocrat
    1.41
    idazole
    1.40
    Activations Density 0.191%

    No Known Activations