© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    references to waste management and recycling processes

    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
    282
    +0.12
    0.7%
    293
    +0.12
    0.7%
    17
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.05
    293
    +0.12
    0.04
    263
    +0.11
    0.11
    Negative Logits
    à±į
    -2.62
    à±ģ
    -2.45
    à°¿
    -2.23
    à±
    -2.08
    áĢº
    -2.00
     audition
    -1.91
    Ī
    -1.84
    à¯ģ
    -1.76
    atinib
    -1.75
     deaf
    -1.70
    POSITIVE LOGITS
     containers
    3.56
     bags
    3.35
     packaging
    3.26
     container
    3.02
     recycl
    2.90
     packing
    2.88
     Pack
    2.87
     cargo
    2.82
     sacks
    2.76
     Container
    2.74
    Activations Density 2.045%

    No Known Activations