© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27390
    Prev
    Next
    INDEX
    Explanations

    technical jargon or terms related to coding or programming

    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
    350
    +0.16
    0.9%
    369
    +0.13
    0.7%
    177
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.16
    0.02
    111
    +0.13
    0.02
    354
    +0.11
    0.01
    Negative Logits
    Ĺ
    -1.55
    £
    -1.54
    Ĥ¬
    -1.50
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.49
    Supporting
    -1.48
    ↵
    -1.48
      ↵
    -1.48
     ↵
    -1.48
    -1.48
    ↵↵
    -1.48
    POSITIVE LOGITS
    ename
    2.01
    iment
    1.90
    emaker
    1.73
    imes
    1.66
    eln
    1.65
    elsen
    1.64
    itud
    1.61
    ilation
    1.61
    etto
    1.61
    estyle
    1.61
    Activations Density 0.123%

    No Known Activations