© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12061
    Prev
    Next
    INDEX
    Explanations

    elements related to memory management and storage architecture in programming

    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
    35
    +0.14
    0.7%
    488
    +0.11
    0.6%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.20
    156
    +0.11
    0.17
    510
    +0.11
    0.12
    Negative Logits
     dermat
    -1.88
     IgE
    -1.83
    asone
    -1.75
     skiing
    -1.73
     allergic
    -1.70
     allerg
    -1.68
     Veter
    -1.67
    CoV
    -1.63
     vaccinated
    -1.62
     veterinary
    -1.61
    POSITIVE LOGITS
     Memory
    3.77
     memory
    3.71
     DRAM
    3.37
     RAM
    3.32
    Memory
    3.23
    memory
    3.15
     mem
    2.94
     memories
    2.94
     DDR
    2.83
    RAM
    2.70
    Activations Density 0.989%

    No Known Activations