© 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. 25167
    Prev
    Next
    INDEX
    Explanations

    terms related to premature birth and miscarriages

    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
    111
    +0.18
    1.0%
    156
    +0.15
    0.9%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.01
    240
    +0.15
    0.01
    444
    +0.10
    0.01
    Negative Logits
    ĥ½
    -3.16
    ľĵ
    -3.10
    Ħ
    -3.09
    Ń
    -3.06
    ı
    -3.05
    Ķ
    -3.00
    ħ
    -2.97
    ŀ
    -2.96
    ¿½
    -2.88
    ľ
    -2.87
    POSITIVE LOGITS
    "}](#
    1.81
    folk
    1.73
     (\>
    1.69
     (>
    1.64
     (\<
    1.57
     \-
    1.54
     (\#
    1.39
    reatment
    1.38
    lag
    1.38
    chap
    1.37
    Activations Density 0.062%

    No Known Activations