© 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. Residuals
    9. 1-RES-SM
    11. 30000
    Prev
    Next
    INDEX
    Explanations

    references to purchasing and buying behaviors

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    1.2%
    174
    +0.15
    0.9%
    376
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.21
    0.05
    252
    +0.15
    0.03
    94
    +0.15
    0.04
    Negative Logits
    ĨĴ
    -2.70
    £
    -2.53
    Ń
    -2.35
    ŀ
    -2.31
    Ĵ
    -2.20
    Ł
    -2.17
    Ŀ
    -2.04
    ©
    -1.99
    Į
    -1.96
    áĢº
    -1.94
    POSITIVE LOGITS
     grocer
    1.70
     goods
    1.63
     apart
    1.56
     tickets
    1.51
     securities
    1.48
     dollars
    1.48
    ftware
    1.44
     notes
    1.44
     commodities
    1.44
    idge
    1.43
    Activations Density 0.259%

    No Known Activations