© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25058
    Prev
    Next
    INDEX
    Explanations

    JSON-like structures and elements related to data organization

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.13
    0.8%
    320
    +0.13
    0.7%
    195
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.13
    0.01
    71
    +0.13
    0.02
    268
    +0.12
    0.01
    Negative Logits
    gree
    -1.34
    ote
    -1.31
     Nintendo
    -1.30
    iosity
    -1.29
     friend
    -1.29
    "</
    -1.28
    izes
    -1.27
    enron
    -1.25
    .\"
    -1.25
     Heroes
    -1.25
    POSITIVE LOGITS
    amsbsy
    1.65
    amsfonts
    1.61
    chitz
    1.59
     brackets
    1.57
    θ
    1.54
    ÏĦαι
    1.54
    orems
    1.50
    yrinth
    1.44
    λ
    1.44
     cases
    1.43
    Activations Density 0.077%

    No Known Activations