© 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. 4-RES-SM
    11. 9965
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is", including its various forms and related phrases

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    337
    +0.21
    1.2%
    152
    +0.16
    0.9%
    235
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.21
    0.06
    83
    +0.16
    0.05
    152
    +0.16
    0.04
    Negative Logits
    sheet
    -1.50
    AGE
    -1.42
    grades
    -1.42
     thereto
    -1.39
    //
    -1.39
    FROM
    -1.37
     rates
    -1.37
    figure
    -1.37
     deal
    -1.36
    irement
    -1.36
    POSITIVE LOGITS
    ħ
    3.26
    ĩ
    3.21
    ı
    3.06
    ¾
    3.02
    ¹
    2.91
    <|outofrange|>
    2.90
    č↵
    2.90
    2.90
    ↵
    2.90
    2.90
    Activations Density 0.258%

    No Known Activations