© 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. 25031
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tail."

    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
    376
    +0.13
    0.7%
    361
    +0.12
    0.7%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.13
    0.01
    155
    +0.12
    0.01
    104
    +0.11
    0.01
    Negative Logits
    stanbul
    -1.71
    undry
    -1.63
    ¨
    -1.52
     both
    -1.44
    Ī
    -1.44
    ly
    -1.40
    yx
    -1.36
    aeda
    -1.34
    '));
    -1.33
    zk
    -1.32
    POSITIVE LOGITS
    lessness
    1.92
    ruptcy
    1.79
     infringement
    1.73
    oring
    1.71
    keeping
    1.69
    gated
    1.68
    amento
    1.68
    bud
    1.68
    ved
    1.65
    oddsidemargin
    1.63
    Activations Density 0.115%

    No Known Activations