© 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. 25010
    Prev
    Next
    INDEX
    Explanations

    references to items and belongings

    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
    156
    +0.21
    1.3%
    376
    +0.15
    0.9%
    502
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.21
    0.03
    241
    +0.15
    0.03
    184
    +0.14
    0.02
    Negative Logits
    -2.21
    ↵
    -2.21
    č↵
    -2.21
     ↵
    -2.21
       ↵
    -2.21
    ↵
    -2.21
    -2.21
    ↵
    -2.21
    ↵
    -2.21
    <|outofrange|>
    -2.21
    POSITIVE LOGITS
    manship
    2.25
    eller
    2.10
    pot
    1.96
    ickness
    1.93
    nel
    1.91
    ellers
    1.78
    mith
    1.75
    ious
    1.69
    elle
    1.67
     contained
    1.66
    Activations Density 0.024%

    No Known Activations