© 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. 9-ATT-KK
    11. 9311
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and variations of it, indicating focus on frequent determiners in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.06
    3:0.05
    4:0.04
    5:0.06
    6:0.20
    7:0.04
    8:0.10
    9:0.21
    10:0.03
    11:0.05
    Negative Logits
     Ott
    -4.47
     Tate
    -3.77
    Ott
    -3.77
    thia
    -3.73
     Si
    -3.58
    Cole
    -3.55
     Ich
    -3.50
     Wis
    -3.45
     Dodd
    -3.40
     Toll
    -3.35
    POSITIVE LOGITS
    Rocket
    9.99
     Rocket
    9.36
     rocket
    8.45
     rockets
    8.34
    rocket
    8.19
     Rockets
    7.25
     launcher
    6.14
     Launcher
    5.94
     launchers
    5.64
     missile
    5.25
    Activations Density 0.004%

    No Known Activations