© 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 EvalsExportsinterp-engineNEWAPI 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. 28174
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and mechanical components

    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
    369
    +0.12
    0.7%
    122
    +0.12
    0.7%
    419
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.12
    0.04
    173
    +0.12
    0.03
    222
    +0.11
    0.04
    Negative Logits
    ĺ
    -1.83
    £
    -1.82
      ↵
    -1.77
    ↵            ↵
    -1.77
    -1.77
    ↵
    -1.77
    <|outofrange|>
    -1.77
    <|outofrange|>
    -1.77
    -1.77
    ↵
    -1.77
    POSITIVE LOGITS
    amento
    2.22
    gage
    2.21
    gue
    1.97
     oneself
    1.77
    sworth
    1.61
    nings
    1.61
     firms
    1.59
    ifice
    1.59
     himself
    1.56
    yst
    1.54
    Activations Density 0.299%

    No Known Activations