© 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. 29788
    Prev
    Next
    INDEX
    Explanations

    the word "satur" and its variations in context, particularly in relation to its use in scientific and technical discussions

    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
    77
    +0.14
    0.8%
    406
    +0.13
    0.7%
    317
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.14
    0.01
    442
    +0.13
    0.01
    406
    +0.12
    0.01
    Negative Logits
     else
    -1.76
     latter
    -1.66
    "))
    -1.61
     ?"
    -1.60
    soever
    -1.60
    "?"
    -1.59
    ).](
    -1.58
    ?"
    -1.58
     string
    -1.55
     bark
    -1.53
    POSITIVE LOGITS
    º
    2.24
    ©
    2.23
    ĻĤ
    2.02
    ¢
    2.00
    ¸
    2.00
    ¹
    1.97
    iop
    1.96
    »¿
    1.90
    ĸ
    1.90
    ł
    1.83
    Activations Density 0.013%

    No Known Activations