© 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. 29876
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities in the text

    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
    456
    +0.14
    0.8%
    167
    +0.13
    0.7%
    64
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.14
    0.06
    166
    +0.13
    0.03
    165
    +0.12
    0.02
    Negative Logits
     CBC
    -1.52
     oneself
    -1.50
     YES
    -1.49
    LEY
    -1.47
    +)
    -1.45
     Commissioner
    -1.45
     society
    -1.41
    aires
    -1.40
    ^+^
    -1.39
     forth
    -1.38
    POSITIVE LOGITS
    »¿
    1.40
     accident
    1.31
    ?>
    1.29
     frequ
    1.28
    ĨĴ
    1.28
    nick
    1.28
    -->
    1.27
     threatened
    1.27
    chle
    1.26
     crashed
    1.25
    Activations Density 0.556%

    No Known Activations