© 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. 24939
    Prev
    Next
    INDEX
    Explanations

    logging levels and status indicators in the text

    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
    503
    +0.15
    0.8%
    376
    +0.13
    0.8%
    187
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.15
    0.01
    503
    +0.13
    0.01
    301
    +0.12
    0.01
    Negative Logits
     blame
    -1.49
     awake
    -1.46
    ?).
    -1.40
    itively
    -1.38
    ausing
    -1.36
    )?
    -1.35
     sweat
    -1.34
    ĥ½
    -1.33
    ductor
    -1.32
    ))?
    -1.29
    POSITIVE LOGITS
    ister
    2.03
    ptions
    1.98
    ppo
    1.76
    bic
    1.66
    illery
    1.65
    isters
    1.65
    edly
    1.54
     estates
    1.54
     estate
    1.49
    clesiast
    1.45
    Activations Density 0.012%

    No Known Activations