© 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. 30954
    Prev
    Next
    INDEX
    Explanations

    references to India

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    321
    +0.15
    0.9%
    71
    +0.14
    0.8%
    382
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.15
    0.03
    227
    +0.14
    0.03
    420
    +0.12
    0.03
    Negative Logits
    quired
    -1.68
    pected
    -1.63
      ↵
    -1.61
    usterity
    -1.59
    ľ
    -1.54
    cluding
    -1.54
     коÑĤоÑĢ
    -1.50
     sentenced
    -1.47
    hentication
    -1.44
    hr
    -1.40
    POSITIVE LOGITS
     herself
    2.03
     itself
    1.95
     themselves
    1.74
    leen
    1.71
    finder
    1.69
    illac
    1.62
    imen
    1.55
     himself
    1.52
    craft
    1.51
    eren
    1.48
    Activations Density 0.020%

    No Known Activations