© 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. 2-RES-SM
    11. 12715
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms associated with leadership or authority figures

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    369
    +0.18
    1.0%
    450
    +0.15
    0.9%
    59
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.18
    0.04
    410
    +0.15
    0.06
    369
    +0.15
    0.03
    Negative Logits
    JUST
    -1.72
    rapeut
    -1.67
    ffect
    -1.63
    ept
    -1.60
    eting
    -1.59
    tig
    -1.57
    hte
    -1.56
    braska
    -1.55
    CDATA
    -1.50
    hering
    -1.50
    POSITIVE LOGITS
    wyn
    1.79
    bage
    1.78
    ½
    1.71
    ·
    1.70
    wen
    1.68
    ney
    1.67
    amycin
    1.66
    nered
    1.63
    wick
    1.61
    down
    1.59
    Activations Density 0.224%

    No Known Activations