© 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. 25197
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific football team, Yeovil

    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
    410
    +0.18
    1.1%
    369
    +0.16
    0.9%
    251
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.18
    0.01
    410
    +0.16
    0.01
    422
    +0.15
    0.01
    Negative Logits
    Ļª
    -2.27
    yx
    -1.73
    ancel
    -1.69
    origin
    -1.65
    yz
    -1.60
    ONS
    -1.54
    ribut
    -1.47
    acial
    -1.46
    rin
    -1.43
    ancell
    -1.42
    POSITIVE LOGITS
    ppo
    2.26
    ÅĽci
    1.72
    houses
    1.57
    ettes
    1.50
     attempt
    1.49
    Å¡ÃŃ
    1.46
    ño
    1.45
     flic
    1.38
    ÅĽ
    1.37
    heart
    1.37
    Activations Density 0.008%

    No Known Activations