© 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. 2-RES-SM
    11. 32416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only" and related terms indicating exclusivity or singularity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    354
    +0.14
    0.8%
    137
    +0.13
    0.7%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.03
    15
    +0.13
    0.03
    130
    +0.11
    0.03
    Negative Logits
    soever
    -1.68
    ivism
    -1.67
    ization
    -1.65
    ttp
    -1.64
    lement
    -1.64
    abad
    -1.61
    hens
    -1.56
    sburg
    -1.55
    ment
    -1.53
    itism
    -1.51
    POSITIVE LOGITS
     ones
    1.84
    Ī
    1.83
    Į
    1.83
    official
    1.76
     conceivable
    1.67
    Ľ
    1.67
    entity
    1.59
     ONE
    1.57
    į
    1.56
     case
    1.53
    Activations Density 0.110%

    No Known Activations