© 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. 31092
    Prev
    Next
    INDEX
    Explanations

    mentions of budget deficits

    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
    474
    +0.13
    0.7%
    415
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.13
    0.01
    474
    +0.12
    0.01
    206
    +0.12
    0.01
    Negative Logits
    thood
    -1.61
    erto
    -1.51
     sarcoma
    -1.50
     parte
    -1.48
    ches
    -1.48
    geant
    -1.43
    derer
    -1.39
     typename
    -1.37
    uginosa
    -1.35
    ^*_
    -1.34
    POSITIVE LOGITS
    ion
    1.60
    ives
    1.59
    posed
    1.52
    obl
    1.48
    point
    1.47
    arial
    1.43
    erve
    1.42
     controls
    1.42
    ary
    1.40
     neutrality
    1.40
    Activations Density 0.012%

    No Known Activations