© 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. 25061
    Prev
    Next
    INDEX
    Explanations

    mentions of America

    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
    +0.16
    0.9%
    457
    +0.15
    0.9%
    105
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.16
    0.04
    457
    +0.15
    0.03
    420
    +0.11
    0.03
    Negative Logits
    TY
    -1.60
     individuals
    -1.55
    rene
    -1.54
    led
    -1.51
    ked
    -1.49
    sing
    -1.43
    inners
    -1.42
    ONS
    -1.42
    ushed
    -1.42
     Appellees
    -1.41
    POSITIVE LOGITS
    ophone
    1.81
    illac
    1.69
    ģ
    1.64
    ¦
    1.56
    ément
    1.55
     expands
    1.51
    ocene
    1.47
    isco
    1.46
     tastes
    1.46
     understands
    1.45
    Activations Density 0.019%

    No Known Activations