© 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 · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15914
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person pronoun "I" and related personal expressions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.37
    2:0.08
    3:0.04
    4:0.06
    5:0.11
    6:0.03
    7:0.05
    8:0.04
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
    avage
    -3.13
    alde
    -2.73
    ogenic
    -2.67
     facial
    -2.62
    venge
    -2.61
    Override
    -2.53
     Total
    -2.47
     Overt
    -2.45
    omo
    -2.42
     residential
    -2.39
    POSITIVE LOGITS
    'd
    6.38
     hadn
    3.39
    Fair
    3.28
     faire
    3.08
     wouldn
    3.07
    've
    3.02
     ain
    2.91
     Wouldn
    2.83
    Far
    2.80
    sure
    2.73
    Activations Density 0.016%

    No Known Activations