© 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. 32359
    Prev
    Next
    INDEX
    Explanations

    references to the GitHub platform

    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
    91
    +0.12
    0.7%
    372
    +0.12
    0.7%
    53
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.12
    0.02
    74
    +0.12
    0.02
    298
    +0.11
    0.02
    Negative Logits
    \[[@
    -1.48
    equ
    -1.42
     jurisdiction
    -1.42
    ful
    -1.42
     ending
    -1.39
    requ
    -1.39
    ce
    -1.35
     appropriate
    -1.34
    few
    -1.33
     jury
    -1.33
    POSITIVE LOGITS
    ĻĤ
    1.80
    ios
    1.73
    owski
    1.48
    bons
    1.48
    ois
    1.45
    jamin
    1.44
     Juda
    1.43
    liest
    1.42
    nil
    1.40
     quotes
    1.39
    Activations Density 0.087%

    No Known Activations