© 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. 25220
    Prev
    Next
    INDEX
    Explanations

    instances of the word "checkout."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.17
    1.0%
    376
    +0.14
    0.8%
    363
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.17
    0.01
    174
    +0.14
    0.01
    40
    +0.12
    0.01
    Negative Logits
    č↵
    -1.91
     ↵
    -1.91
    -1.91
    ↵↵
    -1.91
    -1.91
    <|outofrange|>
    -1.91
    -1.91
    ↵
    -1.91
    <|outofrange|>
    -1.91
     ↵
    -1.91
    POSITIVE LOGITS
     kinematics
    1.68
     notes
    1.65
     schedules
    1.60
    lists
    1.59
     passages
    1.57
    mate
    1.55
    manship
    1.52
    ovic
    1.50
     violates
    1.50
    ató
    1.49
    Activations Density 0.012%

    No Known Activations