© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    terms related to retail and its various aspects

    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
    156
    +0.25
    1.5%
    173
    +0.14
    0.8%
    241
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.25
    0.02
    241
    +0.14
    0.02
    156
    +0.11
    0.02
    Negative Logits
    xico
    -1.75
    usterity
    -1.71
    urane
    -1.61
    ÙĦÙī
    -1.56
     hers
    -1.56
    otypic
    -1.55
    Īĺ
    -1.54
    ermine
    -1.51
    ĨĴ
    -1.50
    assador
    -1.49
    POSITIVE LOGITS
     outlets
    2.00
     sale
    1.72
     sells
    1.69
     marketing
    1.65
     outlet
    1.63
     manager
    1.60
    listed
    1.60
     purchaser
    1.59
     sales
    1.57
    ing
    1.56
    Activations Density 0.150%

    No Known Activations