© 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 EvalsExportsAPI 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. 9948
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Paul."

    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
    156
    +0.21
    1.2%
    410
    +0.17
    0.9%
    369
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.21
    0.04
    369
    +0.17
    0.01
    177
    +0.15
    0.02
    Negative Logits
    ĥ½
    -1.93
    »
    -1.78
    rapeut
    -1.73
    defer
    -1.66
     entire
    -1.56
    ODULE
    -1.56
     sexes
    -1.54
     """
    -1.54
     previous
    -1.50
    pite
    -1.50
    POSITIVE LOGITS
     Getty
    1.91
    rice
    1.88
    son
    1.78
    lein
    1.75
    ucci
    1.73
    stadt
    1.70
    elli
    1.69
    sen
    1.65
     Newman
    1.63
    sson
    1.62
    Activations Density 0.121%

    No Known Activations