© 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. 9-ATT-KK
    11. 10710
    Prev
    Next
    INDEX
    Explanations

    terms related to newsletters and subscription offers from The New York Times

    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
    0:0.14
    1:0.03
    2:0.03
    3:0.17
    4:0.02
    5:0.27
    6:0.04
    7:0.06
    8:0.04
    9:0.02
    10:0.11
    11:0.02
    Negative Logits
     dign
    -2.33
     awarding
    -2.33
     lodge
    -2.23
     homage
    -2.20
     banquet
    -2.19
     salaries
    -2.16
     lavish
    -2.15
     hospitality
    -2.13
     2022
    -2.12
     signage
    -2.11
    POSITIVE LOGITS
    hid
    2.15
     Convers
    2.15
     Myth
    2.04
    ettel
    2.02
     Diary
    1.94
    rom
    1.93
     Synd
    1.92
    errors
    1.92
    ulner
    1.90
    enz
    1.89
    Activations Density 0.010%

    No Known Activations