© 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. 25715
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is" and expressions indicating existence or conditions

    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
    285
    +0.15
    0.8%
    108
    +0.13
    0.7%
    48
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.15
    0.06
    285
    +0.13
    0.06
    431
    +0.12
    0.04
    Negative Logits
    itis
    -1.52
    acs
    -1.51
    ł
    -1.50
    uet
    -1.50
    avirus
    -1.50
     anonymity
    -1.48
    ual
    -1.47
     atrophy
    -1.42
    idase
    -1.41
    ©
    -1.41
    POSITIVE LOGITS
     imagin
    1.44
     ever
    1.42
     direction
    1.37
     hereinafter
    1.37
     hereafter
    1.33
    iances
    1.31
     directions
    1.31
     concerned
    1.29
     negot
    1.26
     kt
    1.23
    Activations Density 0.382%

    No Known Activations