© 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. 31063
    Prev
    Next
    INDEX
    Explanations

    the word "aya" in a variety of contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.17
    1.0%
    450
    +0.13
    0.7%
    246
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.17
    0.01
    450
    +0.13
    0.01
    420
    +0.12
    0.01
    Negative Logits
      ↵
    -1.76
     others
    -1.61
    ![**
    -1.58
    oths
    -1.55
     \%
    -1.50
    úblic
    -1.45
     Mice
    -1.44
     ?"
    -1.40
     thee
    -1.38
    oli
    -1.38
    POSITIVE LOGITS
    bank
    2.13
    ward
    1.80
    lists
    1.74
    yard
    1.65
     wins
    1.64
    ew
    1.63
    istic
    1.61
    velt
    1.59
    guard
    1.57
    izes
    1.56
    Activations Density 0.022%

    No Known Activations