© 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. 31016
    Prev
    Next
    INDEX
    Explanations

    references to something being 'beneath' or 'underneath' various contexts

    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
    +0.17
    1.0%
    243
    +0.15
    0.9%
    107
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.17
    0.02
    243
    +0.15
    0.01
    433
    +0.14
    0.01
    Negative Logits
    apine
    -1.98
    ANS
    -1.87
    ostat
    -1.76
    isters
    -1.65
    rap
    -1.63
    ards
    -1.62
    adian
    -1.57
    SD
    -1.49
    ************************************************************************
    -1.48
    acs
    -1.46
    POSITIVE LOGITS
    ł
    3.01
    Ĥ¬
    2.83
    ĸ´
    2.82
    Īĺ
    2.73
    ↵
    2.73
    2.73
    2.73
    2.73
    2.73
    ↵
    2.73
    Activations Density 1.845%

    No Known Activations