© 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. 31080
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of cuisine or dish

    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
    +0.14
    0.8%
    132
    +0.13
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.14
    0.01
    149
    +0.13
    0.01
    423
    +0.12
    0.01
    Negative Logits
    ivities
    -1.73
    pez
    -1.68
     \*\*
    -1.60
    itched
    -1.56
     both
    -1.56
     each
    -1.48
     their
    -1.46
    grown
    -1.45
    IGH
    -1.45
    aucoup
    -1.44
    POSITIVE LOGITS
    recht
    1.81
    estock
    1.71
    face
    1.66
    eries
    1.65
    ware
    1.64
    emat
    1.62
    fors
    1.60
    enstein
    1.58
    eto
    1.58
    endo
    1.58
    Activations Density 0.011%

    No Known Activations