© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25274
    Prev
    Next
    INDEX
    Explanations

    concepts and motifs related to various themes in literature and culture

    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
    156
    +0.21
    1.2%
    376
    +0.17
    1.0%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.21
    0.01
    365
    +0.17
    0.01
    54
    +0.13
    0.01
    Negative Logits
     preponderance
    -2.02
    jours
    -1.75
    *>
    -1.71
    orems
    -1.70
    bey
    -1.64
    acity
    -1.60
    imits
    -1.59
    ubicin
    -1.52
     generality
    -1.51
     wonders
    -1.50
    POSITIVE LOGITS
    urgical
    1.79
    hip
    1.61
     store
    1.59
    mith
    1.56
     during
    1.54
    hell
    1.53
    ystem
    1.53
    ystems
    1.51
    sheet
    1.51
    pot
    1.49
    Activations Density 0.013%

    No Known Activations