© 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. 25423
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to photography

    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
    +0.17
    0.9%
    100
    +0.14
    0.8%
    359
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.17
    0.02
    230
    +0.14
    0.02
    393
    +0.13
    0.03
    Negative Logits
    ī
    -3.31
    Īĺ
    -3.29
    ¯
    -3.21
    Į
    -3.09
    «
    -3.02
    ↵
    -2.95
    ↵  ↵
    -2.95
    ↵
    -2.95
    ↵
    -2.95
    č↵
    -2.95
    POSITIVE LOGITS
    print
    1.68
    ynthesis
    1.64
    nail
    1.62
    ensitivity
    1.60
    acing
    1.59
     Photograph
    1.58
    igraphy
    1.54
    ogue
    1.53
    ière
    1.52
    ios
    1.50
    Activations Density 0.132%

    No Known Activations