© 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. 24978
    Prev
    Next
    INDEX
    Explanations

    references to quantities or sizes that denote bulk or mass

    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
    +0.12
    0.7%
    333
    +0.11
    0.6%
    232
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.12
    0.02
    232
    +0.11
    0.01
    263
    +0.11
    0.01
    Negative Logits
     same
    -1.79
    naments
    -1.52
     '';
    -1.49
    ibaba
    -1.47
     respondent
    -1.42
     appellants
    -1.41
     Centers
    -1.39
     '../
    -1.37
    respectively
    -1.36
     """
    -1.36
    POSITIVE LOGITS
    ¢
    2.06
    Ļ
    2.00
    «
    1.85
    ģ
    1.83
    µ
    1.79
    ¹
    1.78
    Ģ
    1.75
    Ĵ
    1.74
    ij
    1.67
    ł
    1.66
    Activations Density 0.015%

    No Known Activations