© 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. 14955
    Prev
    Next
    INDEX
    Explanations

    phrases related to remembrance and tribute

    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
    0:0.17
    1:0.15
    2:0.05
    3:0.04
    4:0.03
    5:0.02
    6:0.04
    7:0.08
    8:0.03
    9:0.04
    10:0.25
    11:0.05
    Negative Logits
    ennial
    -3.12
    ł
    -3.11
    enhagen
    -2.93
    intern
    -2.92
    aylor
    -2.87
    yr
    -2.81
    ighth
    -2.72
    issance
    -2.71
     Aberdeen
    -2.67
    acers
    -2.62
    POSITIVE LOGITS
     Ve
    9.83
    Ve
    7.51
     ve
    4.96
     Veg
    4.73
     Veget
    4.55
     Ze
    4.26
    ve
    3.84
     Ha
    3.73
     Pe
    3.70
     Ste
    3.67
    Activations Density 0.002%

    No Known Activations