© 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. 31256
    Prev
    Next
    INDEX
    Explanations

    concepts related to differentiation in various contexts, especially in medical or biological settings

    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
    +0.13
    0.8%
    125
    +0.10
    0.6%
    380
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.01
    337
    +0.10
    0.01
    449
    +0.09
    0.01
    Negative Logits
    ĨĴ
    -2.08
    ĥ½
    -1.89
    chanical
    -1.80
    ¿
    -1.73
    zos
    -1.70
    }|^
    -1.69
    edes
    -1.61
    »¿
    -1.59
    CLA
    -1.59
    IJ
    -1.57
    POSITIVE LOGITS
    arily
    1.72
     apparatus
    1.67
    uary
    1.64
    ually
    1.61
     imped
    1.61
     chambers
    1.61
     positions
    1.57
    eral
    1.55
     position
    1.54
     venue
    1.54
    Activations Density 1.281%

    No Known Activations