© 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. 31229
    Prev
    Next
    INDEX
    Explanations

    specific instances of numerical values and monetary amounts

    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
    407
    +0.12
    0.7%
    463
    +0.10
    0.5%
    96
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.12
    0.40
    53
    +0.10
    0.42
    56
    +0.09
    0.11
    Negative Logits
     Invention
    -1.66
     submit
    -1.43
     same
    -1.43
     Gaz
    -1.35
    ctin
    -1.35
     annual
    -1.35
    «
    -1.34
    jobs
    -1.33
     spouses
    -1.33
     Encyclopedia
    -1.31
    POSITIVE LOGITS
    ports
    1.78
    directed
    1.68
    posed
    1.64
    rade
    1.56
    riend
    1.56
    optional
    1.55
    ary
    1.48
    iously
    1.46
    hops
    1.45
    charged
    1.43
    Activations Density 4.644%

    No Known Activations