© 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. 24934
    Prev
    Next
    INDEX
    Explanations

    terms related to negative medical conditions

    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
    156
    +0.20
    1.2%
    67
    +0.14
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.20
    0.01
    452
    +0.14
    0.01
    488
    +0.13
    0.01
    Negative Logits
    ½
    -1.77
    ĥ½
    -1.67
     '</
    -1.45
    reek
    -1.44
    ĨĴ
    -1.42
    ©
    -1.39
    lick
    -1.38
    hing
    -1.38
     /></
    -1.37
     rinsed
    -1.35
    POSITIVE LOGITS
     ones
    2.03
    ieri
    1.81
    imize
    1.77
    emente
    1.75
     situations
    1.74
     minded
    1.74
     occasions
    1.67
     areas
    1.66
    guy
    1.61
    enough
    1.59
    Activations Density 0.011%

    No Known Activations