© 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. 4-RES-SM
    11. 9780
    Prev
    Next
    INDEX
    Explanations

    references to event-driven programming and countdown events

    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
    55
    +0.13
    0.7%
    235
    +0.12
    0.7%
    210
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.13
    0.05
    47
    +0.12
    0.06
    484
    +0.11
    0.03
    Negative Logits
     vocational
    -1.79
     textbooks
    -1.69
    DIG
    -1.68
     cellulose
    -1.67
    8859
    -1.63
    phabet
    -1.51
     rank
    -1.49
    acrylamide
    -1.48
    fonts
    -1.46
    ascii
    -1.44
    POSITIVE LOGITS
     Event
    4.01
     event
    3.84
     events
    3.76
    events
    3.62
    event
    3.60
     Events
    3.57
    Event
    3.52
     EVENT
    3.37
    EVENT
    3.32
    EventListener
    3.27
    Activations Density 1.229%

    No Known Activations