© 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. 25036
    Prev
    Next
    INDEX
    Explanations

    mentions of the region Yorkshire, specifically the city of Leeds

    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
    156
    +0.17
    1.0%
    71
    +0.16
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.17
    0.01
    222
    +0.16
    0.01
    419
    +0.14
    0.01
    Negative Logits
    ĥ½
    -1.91
    ı
    -1.87
    İ
    -1.81
    Ĩ
    -1.81
     serving
    -1.81
    ħ
    -1.78
    ras
    -1.72
    ij
    -1.71
    ĵ
    -1.64
    ļ
    -1.63
    POSITIVE LOGITS
    vist
    2.12
    selves
    1.73
    hurst
    1.73
    idine
    1.70
    àµį
    1.70
    shire
    1.64
    ingly
    1.63
    film
    1.60
     herself
    1.53
    bourne
    1.52
    Activations Density 0.010%

    No Known Activations