© 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. 31177
    Prev
    Next
    INDEX
    Explanations

    patterns of data in arrays or lists

    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
    478
    +0.19
    1.1%
    23
    +0.15
    0.9%
    188
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.19
    0.02
    51
    +0.15
    0.01
    79
    +0.15
    0.02
    Negative Logits
    istry
    -1.66
     (£
    -1.59
    book
    -1.53
     Tonight
    -1.51
     (`
    -1.50
    week
    -1.49
     (âĪĴ
    -1.46
    books
    -1.45
    adin
    -1.45
    azine
    -1.43
    POSITIVE LOGITS
    İ
    2.70
    °
    2.55
    ĻĤ
    2.38
    unreadable
    2.33
    ¥
    2.31
    Ī
    2.29
    ĥ
    2.26
    Ķ
    2.24
    ¿½
    2.19
    Į
    2.13
    Activations Density 0.673%

    No Known Activations