© 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. 25191
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lost" or phrases indicating loss or giving up

    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
    126
    +0.12
    0.7%
    18
    +0.12
    0.7%
    259
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.12
    0.08
    68
    +0.12
    0.06
    456
    +0.11
    0.06
    Negative Logits
     equivalents
    -1.53
    ÃĹ
    -1.52
    /#
    -1.48
     alt
    -1.47
    IZE
    -1.46
    BI
    -1.46
    /">
    -1.45
    $.[]{
    -1.39
    Inf
    -1.39
    ounds
    -1.37
    POSITIVE LOGITS
    º
    2.06
    ¢
    1.66
    Īĺ
    1.65
    soluble
    1.64
    ↵  ³³³
    1.60
    1.60
    ↵
    1.60
    ↵
    1.60
    ↵↵
    1.60
    1.60
    Activations Density 0.069%

    No Known Activations