© 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. 2-MLP-SM
    11. 22337
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific place names

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.35
    2.0%
    455
    +0.16
    0.9%
    63
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.35
    0.11
    332
    +0.16
    0.09
    119
    +0.13
    0.06
    Negative Logits
    abase
    -1.83
    doms
    -1.75
    writers
    -1.72
    uelle
    -1.70
     estates
    -1.68
     constitu
    -1.60
    ña
    -1.55
    mont
    -1.50
     Tours
    -1.50
     Estate
    -1.49
    POSITIVE LOGITS
    ]{.
    2.10
    '?"
    1.94
    $]{}
    1.56
     adults
    1.55
     fuzzy
    1.51
    ]{
    1.49
    ĻĤ
    1.49
    ithmic
    1.48
     infants
    1.47
    ?'
    1.45
    Activations Density 1.259%

    No Known Activations