© 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. 25300
    Prev
    Next
    INDEX
    Explanations

    the term "Med" which likely refers to medical contexts or terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.15
    0.9%
    2
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.15
    0.01
    328
    +0.14
    0.01
    281
    +0.12
    0.01
    Negative Logits
    oming
    -1.85
    aming
    -1.65
    ses
    -1.55
    mo
    -1.38
     maternal
    -1.37
     mening
    -1.37
    asts
    -1.36
    aphyl
    -1.36
    auc
    -1.36
     tires
    -1.35
    POSITIVE LOGITS
    iator
    2.05
    ieux
    1.92
    ieval
    1.77
    scape
    1.74
    º
    1.73
    fiddle
    1.71
    iterr
    1.70
    ulator
    1.65
    iale
    1.61
    align
    1.55
    Activations Density 0.479%

    No Known Activations