© 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. 29131
    Prev
    Next
    INDEX
    Explanations

    forms of the word "to"

    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
    69
    +0.19
    1.1%
    478
    +0.15
    0.9%
    320
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.19
    0.06
    411
    +0.15
    0.04
    328
    +0.13
    0.04
    Negative Logits
    ®
    -2.60
    ĻĤ
    -2.13
    ¨
    -1.91
    ¢
    -1.91
    ¾
    -1.76
    ĸ
    -1.76
    Ĵ
    -1.74
    §
    -1.70
    ĨĴ
    -1.69
    İ
    -1.69
    POSITIVE LOGITS
     answer
    1.80
     proceed
    1.72
     arbit
    1.70
     respondent
    1.68
     satisfy
    1.64
     judge
    1.63
     petitioner
    1.63
    pless
    1.59
    quez
    1.56
     be
    1.56
    Activations Density 0.277%

    No Known Activations