© 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. 28485
    Prev
    Next
    INDEX
    Explanations

    words related to the United States

    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
    273
    +0.14
    0.8%
    88
    +0.13
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.14
    0.04
    88
    +0.13
    0.05
    188
    +0.13
    0.03
    Negative Logits
    sible
    -1.94
    onym
    -1.72
    onymous
    -1.59
     wrong
    -1.50
    furt
    -1.44
     error
    -1.44
    '):
    -1.43
     correct
    -1.40
     shame
    -1.39
     clicks
    -1.38
    POSITIVE LOGITS
    ERIAL
    1.82
    ARY
    1.70
    ymphony
    1.63
    erm
    1.59
    agara
    1.52
    TEGER
    1.52
    *âĢIJ
    1.51
    ullivan
    1.47
    ensors
    1.47
    à±ģ
    1.47
    Activations Density 0.082%

    No Known Activations