© 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. 31095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "match" 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
    376
    +0.18
    1.0%
    487
    +0.13
    0.7%
    140
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.18
    0.03
    0
    +0.13
    0.03
    140
    +0.11
    0.02
    Negative Logits
    ERE
    -1.66
    ounder
    -1.64
    áĢ¯
    -1.63
    obbsee
    -1.57
    àµį
    -1.57
    EVER
    -1.52
    irth
    -1.50
    ORK
    -1.49
    ugh
    -1.48
    apine
    -1.48
    POSITIVE LOGITS
     instrument
    1.79
    rooms
    1.71
    making
    1.68
    bag
    1.67
     instruments
    1.62
     area
    1.62
     poses
    1.62
    cases
    1.61
    ties
    1.59
     rooms
    1.58
    Activations Density 0.099%

    No Known Activations