© 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. 31001
    Prev
    Next
    INDEX
    Explanations

    references to significant historical texts or documents

    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
    +0.14
    0.8%
    489
    +0.14
    0.8%
    256
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.14
    0.01
    276
    +0.14
    0.01
    465
    +0.12
    0.01
    Negative Logits
    ..."
    -1.81
     âĻª"
    -1.80
    "?"
    -1.77
     ?"
    -1.73
    ...?"
    -1.70
    '">
    -1.60
    '?"
    -1.55
    "?
    -1.52
     ."
    -1.50
    *>
    -1.48
    POSITIVE LOGITS
    borg
    1.56
     campaigns
    1.53
     oath
    1.49
     campaign
    1.49
     adjuvant
    1.46
    ér
    1.45
    feld
    1.44
    ieu
    1.42
    iculously
    1.40
     costs
    1.40
    Activations Density 0.024%

    No Known Activations