© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12931
    Prev
    Next
    INDEX
    Explanations

    references to specific years and events related to film or notable moments

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    427
    +0.15
    0.8%
    166
    +0.12
    0.7%
    78
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.07
    156
    +0.12
    0.08
    71
    +0.11
    0.04
    Negative Logits
    ViewById
    -1.78
     Android
    -1.69
     Levi
    -1.65
    scala
    -1.62
    android
    -1.62
    Inflater
    -1.57
    Android
    -1.57
    map
    -1.54
     Pradesh
    -1.54
     QT
    -1.54
    POSITIVE LOGITS
     1984
    2.94
     1987
    2.93
     1985
    2.93
     1982
    2.92
     1986
    2.91
     1981
    2.89
     1988
    2.70
     1983
    2.65
     1980
    2.65
     1989
    2.58
    Activations Density 1.057%

    No Known Activations