© 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. 29832
    Prev
    Next
    INDEX
    Explanations

    instances of copyright statements or notices

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.19
    1.1%
    258
    +0.18
    1.1%
    203
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.19
    0.05
    203
    +0.18
    0.05
    271
    +0.15
    -0.00
    Negative Logits
    stown
    -1.64
    oks
    -1.64
    etica
    -1.63
    fecture
    -1.57
    buntu
    -1.54
    arts
    -1.51
    ECD
    -1.51
     itself
    -1.50
    eti
    -1.46
    ague
    -1.45
    POSITIVE LOGITS
     privileges
    1.56
    available
    1.56
     WARRANTIES
    1.55
    INESS
    1.42
     _
    1.41
     permission
    1.39
     millions
    1.39
    SYMBOL
    1.38
    ricular
    1.37
     availability
    1.33
    Activations Density 0.345%

    No Known Activations