© 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. 31169
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific numeric value and its context within the document

    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
    458
    +0.15
    0.9%
    369
    +0.15
    0.8%
    477
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.15
    0.04
    409
    +0.15
    0.04
    492
    +0.15
    0.04
    Negative Logits
    quier
    -1.78
    commerce
    -1.59
    blogspot
    -1.52
     manufacture
    -1.50
     Nation
    -1.40
     capitalism
    -1.39
    ...](
    -1.39
     hospitality
    -1.38
     Wars
    -1.38
    merce
    -1.38
    POSITIVE LOGITS
    ³
    3.71
    ª
    3.27
    µ
    3.21
    ĥ½
    3.17
    ¶
    3.09
    ¾
    3.05
    Į
    3.00
    ĺ
    3.00
    Ľ
    2.98
    ¦
    2.97
    Activations Density 0.616%

    No Known Activations