© 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. 9404
    Prev
    Next
    INDEX
    Explanations

    concepts related to reproduction and health impacts

    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
    +0.15
    0.9%
    441
    +0.12
    0.7%
    115
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.38
    156
    +0.12
    0.29
    71
    +0.10
    0.29
    Negative Logits
     widths
    -1.54
     value
    -1.48
    omatic
    -1.47
     controls
    -1.46
     users
    -1.46
     choice
    -1.45
     values
    -1.43
     Wikipedia
    -1.41
     utility
    -1.40
     paper
    -1.40
    POSITIVE LOGITS
    and
    1.88
    ----------------------------------------------------------------------------------------------------------------
    1.87
    himself
    1.82
    ------------------------------------------------------------------------------------------------
    1.79
    Č
    1.77
    thems
    1.75
    --------------------------------------------------------------------------------
    1.72
    ======
    1.71
    ================================================================
    1.68
    º
    1.65
    Activations Density 1.142%

    No Known Activations