© 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. 2-RES-SM
    11. 31067
    Prev
    Next
    INDEX
    Explanations

    the pronoun "they" and its variations in context

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    130
    +0.15
    0.8%
    344
    +0.12
    0.7%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.15
    0.09
    130
    +0.12
    0.09
    284
    +0.12
    0.07
    Negative Logits
    ļ
    -2.10
    º
    -1.79
    Ļª
    -1.73
    °
    -1.71
     itself
    -1.71
    »¿
    -1.70
     its
    -1.69
    ¡
    -1.66
    ¤
    -1.62
    Īĺ
    -1.62
    POSITIVE LOGITS
    efore
    2.32
    're
    2.27
    athered
    1.97
    unnumbered
    1.77
    'd
    1.74
    pherd
    1.72
    'll
    1.70
    quez
    1.68
    aken
    1.66
    renn
    1.66
    Activations Density 0.437%

    No Known Activations