© 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. 25026
    Prev
    Next
    INDEX
    Explanations

    the word "DET" in various contexts

    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
    369
    +0.15
    0.9%
    71
    +0.14
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    111
    +0.14
    0.01
    348
    +0.12
    0.01
    Negative Logits
     small
    -1.89
    Ł
    -1.85
     full
    -1.79
     large
    -1.69
    Ī
    -1.63
     distributed
    -1.63
    hip
    -1.57
     dilated
    -1.57
     remote
    -1.47
    my
    -1.46
    POSITIVE LOGITS
    igue
    2.10
    ière
    2.05
    ridge
    1.78
    ű
    1.73
     Rptr
    1.72
    tech
    1.72
    Bank
    1.71
     shots
    1.70
    ios
    1.69
    ior
    1.67
    Activations Density 0.014%

    No Known Activations