© 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. 31026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "buying" or related terms associated with purchasing actions

    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
    +0.23
    1.3%
    376
    +0.20
    1.1%
    474
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.23
    0.02
    393
    +0.20
    0.02
    252
    +0.13
    0.02
    Negative Logits
    uration
    -1.55
    sburg
    -1.49
    allo
    -1.47
    arers
    -1.46
    ÑģÑĤва
    -1.43
     screening
    -1.42
    à±ģ
    -1.40
    sal
    -1.38
    orect
    -1.38
    ĨĴ
    -1.38
    POSITIVE LOGITS
     instruments
    1.89
     apart
    1.62
     possessions
    1.57
     holes
    1.54
     documents
    1.54
     issues
    1.49
     grip
    1.47
     problems
    1.47
     items
    1.46
     difficulties
    1.44
    Activations Density 0.347%

    No Known Activations