© 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. 12693
    Prev
    Next
    INDEX
    Explanations

    elements related to web development and JavaScript

    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
    312
    +0.14
    0.8%
    339
    +0.12
    0.7%
    98
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    312
    +0.14
    0.05
    74
    +0.12
    0.04
    79
    +0.11
    0.04
    Negative Logits
     Mississippi
    -1.52
    ipal
    -1.48
     deficit
    -1.43
     Black
    -1.37
    ulent
    -1.34
    ocated
    -1.33
     Harvard
    -1.33
    diagonal
    -1.33
    African
    -1.33
     Confederate
    -1.31
    POSITIVE LOGITS
    º
    2.63
    ·¸
    2.45
    °
    2.37
    ĭ
    2.26
    ¸
    2.25
    ¿
    2.24
    ¦
    2.20
    ´
    2.15
    µ
    2.15
    §
    2.08
    Activations Density 0.331%

    No Known Activations