© 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. MLP Post
    9. 0-MLP-SM
    11. 26709
    Prev
    Next
    INDEX
    Explanations

    the name "Timothy" and references to "Corinth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.14
    0.8%
    251
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.14
    0.01
    363
    +0.12
    0.01
    469
    +0.12
    0.01
    Negative Logits
     particular
    -1.74
    TRODUCTION
    -1.67
     previous
    -1.66
    usterity
    -1.61
    Respond
    -1.55
    ı
    -1.54
    rier
    -1.52
    onal
    -1.50
    ĥ½
    -1.50
     former
    -1.49
    POSITIVE LOGITS
    quito
    1.68
    uelle
    1.61
    rill
    1.60
    directed
    1.59
     arrow
    1.54
     Snyder
    1.51
    cules
    1.50
    pson
    1.50
    tie
    1.50
    iana
    1.46
    Activations Density 0.423%

    No Known Activations