© 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. 21637
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word 'that' or its variations, often reflecting a narrative or argumentative structure in the text

    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
    0:0.05
    1:0.03
    2:0.12
    3:0.09
    4:0.14
    5:0.10
    6:0.05
    7:0.04
    8:0.03
    9:0.19
    10:0.04
    11:0.07
    Negative Logits
    keys
    -2.51
    ifter
    -2.32
    azeera
    -2.29
    icks
    -2.24
    arius
    -2.23
    inas
    -2.23
    IONS
    -2.22
    illo
    -2.20
    agos
    -2.18
    enko
    -2.17
    POSITIVE LOGITS
    �
    4.13
     �
    3.34
    �
    2.83
    �
    2.73
    ■
    2.47
    �
    2.45
     \(\
    2.43
    ¨
    2.42
    ̶
    2.39
    .—
    2.39
    Activations Density 0.065%

    No Known Activations