© 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. 2-RES-SM
    11. 26246
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.63
    5.4%
    156
    +0.52
    4.5%
    478
    +0.08
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.63
    0.10
    156
    +0.52
    0.09
    473
    +0.08
    0.09
    Negative Logits
    Ľ
    -4.60
    ®
    -4.56
    ħ
    -4.49
    ¾
    -4.45
    ŀ
    -4.33
    ij
    -4.33
    ĥ½
    -4.30
    ĸ
    -4.30
    ĥ
    -4.25
    £
    -4.23
    POSITIVE LOGITS
     simple
    1.26
    vereign
    1.22
     money
    1.20
     Parenthood
    1.14
     those
    1.13
     food
    1.13
     its
    1.11
    edly
    1.11
    prove
    1.11
    arten
    1.11
    Activations Density 0.126%

    No Known Activations