© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14798
    Prev
    Next
    INDEX
    Explanations

    cases of historical racial injustice and personal struggle

    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
    0:0.22
    1:0.08
    2:0.10
    3:0.03
    4:0.02
    5:0.02
    6:0.12
    7:0.10
    8:0.01
    9:0.05
    10:0.14
    11:0.05
    Negative Logits
    lez
    -3.48
    gnu
    -3.16
     Pyr
    -3.04
    lap
    -3.02
     Lap
    -2.92
     nar
    -2.88
    dx
    -2.87
     Sylv
    -2.87
    oké
    -2.83
     Ys
    -2.81
    POSITIVE LOGITS
     Baker
    9.64
     baker
    4.75
     bake
    4.24
    aker
    4.20
     Mason
    4.10
     Burgess
    4.02
     baking
    3.99
     Bak
    3.98
     Bentley
    3.88
     Hutchinson
    3.83
    Activations Density 0.011%

    No Known Activations