© 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. 10543
    Prev
    Next
    INDEX
    Explanations

    calls to action related to engagement and support for a cause

    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
    0:0.11
    1:0.02
    2:0.07
    3:0.08
    4:0.10
    5:0.14
    6:0.09
    7:0.04
    8:0.19
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
     Fighters
    -3.69
     Aki
    -3.23
     Eliot
    -3.16
    Lv
    -3.11
     Ike
    -3.07
     Zelda
    -2.99
    hin
    -2.94
     Uk
    -2.93
    nces
    -2.80
    闘
    -2.78
    POSITIVE LOGITS
     habitable
    3.69
     Martian
    3.46
     Planetary
    3.28
     gravitational
    3.20
     spac
    3.19
     Nasa
    3.08
     planetary
    3.08
    Planet
    3.01
     civilisation
    2.99
     astronauts
    2.97
    Activations Density 0.004%

    No Known Activations