© 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. 1-RES-SM
    11. 29463
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Par," indicating a focus on mentions of a specific entity or name

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    502
    +0.16
    0.9%
    369
    +0.12
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.03
    181
    +0.12
    0.02
    59
    +0.12
    0.02
    Negative Logits
    ³
    -3.26
    ĥ½
    -3.25
    Ń
    -3.13
    ¢
    -2.94
    ¥
    -2.90
    ¸
    -2.89
    ľĵ
    -2.79
    »
    -2.76
    ĸ´
    -2.75
    ¡
    -2.73
    POSITIVE LOGITS
    agraph
    2.59
    leys
    1.99
    ley
    1.75
    lee
    1.72
    leen
    1.65
    cels
    1.65
     sized
    1.59
    fileID
    1.58
    allel
    1.56
    ais
    1.54
    Activations Density 0.052%

    No Known Activations