© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8901
    Prev
    Next
    INDEX
    Explanations

    references to people and entities involved in personal or business relationships

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.06
    4:0.03
    5:0.03
    6:0.14
    7:0.04
    8:0.04
    9:0.43
    10:0.04
    11:0.04
    Negative Logits
     Gears
    -4.02
     Teg
    -3.98
     Asus
    -3.81
     Gund
    -3.79
     Gol
    -3.78
    gil
    -3.73
     gol
    -3.69
     Je
    -3.60
     Gum
    -3.57
     Bog
    -3.55
    POSITIVE LOGITS
    ister
    6.80
    ISTER
    6.40
    isters
    5.36
     Sister
    4.25
    istered
    3.96
     Mister
    3.89
    cock
    3.87
     McKenna
    3.81
    323
    3.78
    ornia
    3.78
    Activations Density 0.000%

    No Known Activations