© 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. 10314
    Prev
    Next
    INDEX
    Explanations

    references to licensing and ownership in legal or software contexts

    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
    280
    +0.16
    0.9%
    21
    +0.16
    0.9%
    488
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.16
    0.01
    441
    +0.16
    0.01
    59
    +0.11
    0.02
    Negative Logits
     %>%
    -1.77
    ↵
    -1.67
    ↵
    -1.67
    ↵  Âł
    -1.67
    ↵
    -1.67
              ↵
    -1.67
    -1.67
    -1.67
     ↵
    -1.67
    -1.67
    POSITIVE LOGITS
    exception
    1.82
    Otherwise
    1.74
    If
    1.69
    Version
    1.66
    Acknowled
    1.62
    Thus
    1.61
    Permission
    1.58
    Please
    1.57
    ом
    1.57
    ****************************************************************************
    1.54
    Activations Density 0.071%

    No Known Activations