© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27132
    Prev
    Next
    INDEX
    Explanations

    references to the name "Looney" or related variations, indicating a focus on Looney Tunes or associated characters

    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
    406
    +0.14
    0.8%
    410
    +0.12
    0.7%
    338
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.14
    0.02
    406
    +0.12
    0.02
    109
    +0.12
    0.01
    Negative Logits
    áĢº
    -1.83
    lines
    -1.82
    line
    -1.82
    board
    -1.68
    "}](#
    -1.63
    rael
    -1.61
    thia
    -1.58
    phrine
    -1.52
    ĨĴ
    -1.48
    mentation
    -1.46
    POSITIVE LOGITS
     mismo
    1.98
    zier
    1.78
    ft
    1.77
    fts
    1.71
    jo
    1.63
    ÅĽÄĩ
    1.60
    ilo
    1.59
    amento
    1.55
    acks
    1.52
    inters
    1.51
    Activations Density 0.090%

    No Known Activations