© 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. 25091
    Prev
    Next
    INDEX
    Explanations

    references to shopping and shopping-related activities

    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
    +0.18
    1.1%
    173
    +0.16
    0.9%
    241
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.18
    0.03
    241
    +0.16
    0.02
    178
    +0.12
    0.02
    Negative Logits
    Į
    -3.05
    ľ
    -3.04
    ĥ½
    -2.83
    §
    -2.77
    «
    -2.73
    ĸ´
    -2.72
    ļ
    -2.69
    ĨĴ
    -2.66
    Ŀ
    -2.59
    ŀ
    -2.59
    POSITIVE LOGITS
    eer
    1.88
    bags
    1.83
     buys
    1.76
     analyst
    1.73
    place
    1.73
     lanes
    1.60
     seller
    1.60
     trips
    1.60
     outlets
    1.54
    yards
    1.54
    Activations Density 0.135%

    No Known Activations