© 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. 31031
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses in the text

    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
    37
    +0.15
    0.8%
    340
    +0.15
    0.8%
    363
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.15
    0.24
    486
    +0.15
    0.16
    154
    +0.14
    0.15
    Negative Logits
    wered
    -1.70
     outlet
    -1.53
    ViewById
    -1.52
     agenda
    -1.49
    rieved
    -1.44
    rove
    -1.43
    IVATE
    -1.38
    het
    -1.36
    igos
    -1.35
    EMPT
    -1.33
    POSITIVE LOGITS
    ¦
    2.16
    ¡
    1.91
    µ
    1.87
    ĩ
    1.81
    anium
    1.80
    so
    1.70
    ĸ
    1.70
    ©
    1.70
    Ĵ
    1.69
    ¨
    1.68
    Activations Density 0.352%

    No Known Activations