© 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. 14431
    Prev
    Next
    INDEX
    Explanations

    the word "the."

    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
    271
    +0.17
    1.0%
    78
    +0.16
    0.9%
    314
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    0.02
    14
    +0.16
    0.02
    10
    +0.11
    0.02
    Negative Logits
    terest
    -1.75
    tered
    -1.74
    hoe
    -1.61
    ITED
    -1.58
    ched
    -1.55
    ized
    -1.53
    pile
    -1.52
    wise
    -1.50
    ities
    -1.49
    yards
    -1.45
    POSITIVE LOGITS
    reshold
    2.51
    ousand
    1.92
    irst
    1.86
    ousands
    1.79
    rone
    1.78
    icken
    1.73
    unders
    1.70
    arg
    1.68
    ief
    1.66
    resholds
    1.61
    Activations Density 0.061%

    No Known Activations