© 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. 29699
    Prev
    Next
    INDEX
    Explanations

    the word "or" in various contexts throughout the document

    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
    478
    +0.14
    0.8%
    172
    +0.11
    0.7%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.14
    0.02
    172
    +0.11
    0.02
    209
    +0.11
    0.02
    Negative Logits
    ľĵ
    -1.93
    ¢
    -1.71
    :--
    -1.68
    ł
    -1.63
    INGTON
    -1.63
    Į
    -1.60
    []{
    -1.56
    }))
    -1.54
    ening
    -1.51
    Ł
    -1.47
    POSITIVE LOGITS
    naments
    1.47
     pronounce
    1.38
    psin
    1.37
     its
    1.37
    leans
    1.35
    idity
    1.35
    ebook
    1.34
     abide
    1.34
     flavors
    1.27
    IENT
    1.27
    Activations Density 0.091%

    No Known Activations