© 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. 31158
    Prev
    Next
    INDEX
    Explanations

    mentions of exceptions and error handling in programming 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
    475
    +0.12
    0.7%
    67
    +0.11
    0.6%
    503
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.12
    0.03
    67
    +0.11
    0.03
    273
    +0.10
    0.03
    Negative Logits
    ?”
    -1.65
    'll
    -1.57
    "?
    -1.55
    "?"
    -1.49
     gonna
    -1.48
    ?’
    -1.47
    omitempty
    -1.47
    ”?
    -1.47
     your
    -1.46
     searched
    -1.45
    POSITIVE LOGITS
    ļ
    1.93
    ¡
    1.85
    naire
    1.83
    ł
    1.79
    ¦
    1.78
    ¾
    1.77
     era
    1.74
    £
    1.73
    enstein
    1.61
    ©
    1.58
    Activations Density 0.204%

    No Known Activations