© 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. 13434
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals associated with reporting or journalism

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.10
    4:0.11
    5:0.32
    6:0.03
    7:0.01
    8:0.18
    9:0.11
    10:0.02
    11:0.01
    Negative Logits
    ":{"
    -3.30
     (~
    -2.94
     alot
    -2.75
     �
    -2.73
     EVERY
    -2.67
     somet
    -2.63
    ":[{"
    -2.54
     �
    -2.50
     conclud
    -2.48
     blush
    -2.47
    POSITIVE LOGITS
    ;
    5.17
    .;
    4.80
     ;
    4.06
    ';
    3.69
    ";
    3.51
    ;"
    3.43
    %;
    3.41
    ;;
    3.15
    ;;;;;;;;
    3.10
    );
    3.04
    Activations Density 0.003%

    No Known Activations