© 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. 25025
    Prev
    Next
    INDEX
    Explanations

    instances of reference to trade or economic policies

    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
    445
    +0.16
    0.9%
    454
    +0.14
    0.8%
    14
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.16
    0.43
    209
    +0.14
    0.28
    402
    +0.11
    0.25
    Negative Logits
    otti
    -1.57
    iner
    -1.54
    sson
    -1.54
    ogue
    -1.53
    ETHOD
    -1.52
    urope
    -1.51
    ino
    -1.44
    ione
    -1.44
    inners
    -1.43
    avour
    -1.43
    POSITIVE LOGITS
    ched
    1.70
    )->
    1.70
     stack
    1.54
    ķ
    1.52
    lar
    1.48
     amount
    1.46
     load
    1.43
     heap
    1.43
     borders
    1.42
    ()->
    1.39
    Activations Density 1.613%

    No Known Activations