© 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. 24745
    Prev
    Next
    INDEX
    Explanations

    characters or symbols with significant emotional or thematic impact

    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
    478
    +0.16
    0.9%
    480
    +0.14
    0.8%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.16
    0.07
    332
    +0.14
    0.05
    377
    +0.12
    0.06
    Negative Logits
    bserver
    -1.70
    amycin
    -1.68
    ellar
    -1.59
    oque
    -1.59
    áĢº
    -1.48
    ry
    -1.47
    anto
    -1.47
    anda
    -1.46
     listings
    -1.46
     gear
    -1.46
    POSITIVE LOGITS
    Ĺ
    1.74
    ¥
    1.74
    ĺ
    1.71
    Ķ
    1.67
    ļ
    1.60
     ours
    1.54
    namely
    1.54
    Īĺ
    1.54
    hti
    1.51
    either
    1.49
    Activations Density 0.560%

    No Known Activations