© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8924
    Prev
    Next
    INDEX
    Explanations

    the word "have" in various contexts

    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
    289
    +0.14
    0.8%
    151
    +0.12
    0.7%
    235
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.14
    0.05
    402
    +0.12
    0.05
    8
    +0.11
    0.03
    Negative Logits
    Ļª
    -2.06
    imize
    -1.82
    ĸ´
    -1.80
    Ľ
    -1.73
    face
    -1.62
    oddsidemargin
    -1.59
    oracle
    -1.58
    erialize
    -1.55
    imum
    -1.55
    ĩ
    -1.53
    POSITIVE LOGITS
     been
    2.56
     shown
    2.29
     demonstrated
    2.19
     explored
    2.02
     reported
    1.98
     examined
    1.95
     conducted
    1.94
     endeav
    1.92
     systematically
    1.90
     begun
    1.90
    Activations Density 0.114%

    No Known Activations