© 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 · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10767
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" and other personal pronouns indicating personal opinions or agency

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.05
    2:0.30
    3:0.03
    4:0.10
    5:0.13
    6:0.03
    7:0.12
    8:0.06
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Winged
    -3.27
    idable
    -2.87
    undred
    -2.84
    614
    -2.79
    ワン
    -2.67
     Zur
    -2.63
     Qiao
    -2.59
     Finch
    -2.53
    sie
    -2.51
     Puzzles
    -2.50
    POSITIVE LOGITS
     should
    6.11
    should
    5.78
     shouldn
    5.43
     SHOULD
    4.89
    Should
    4.75
     Should
    4.66
     ought
    4.65
    ................................................................
    3.10
    ](
    3.07
    otin
    2.95
    Activations Density 0.084%

    No Known Activations