© 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. 32214
    Prev
    Next
    INDEX
    Explanations

    usage and references to functions or methods in programming contexts

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    231
    +0.12
    0.7%
    465
    +0.11
    0.6%
    95
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.12
    0.05
    256
    +0.11
    0.05
    95
    +0.11
    0.05
    Negative Logits
    ublin
    -1.56
    midt
    -1.51
    sein
    -1.48
    pard
    -1.45
    icz
    -1.40
    mit
    -1.40
    lat
    -1.40
    ism
    -1.39
    ICH
    -1.38
    ios
    -1.38
    POSITIVE LOGITS
     sparing
    1.86
     them
    1.75
     whatever
    1.62
    orm
    1.49
     simulator
    1.48
    pad
    1.48
     lately
    1.48
     tracker
    1.46
     moderation
    1.45
     these
    1.45
    Activations Density 0.189%

    No Known Activations