© 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. 18907
    Prev
    Next
    INDEX
    Explanations

    references to political and racial issues

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.05
    4:0.05
    5:0.05
    6:0.06
    7:0.04
    8:0.40
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
     Canary
    -4.55
     Ö
    -3.99
    usalem
    -3.79
     Zot
    -3.73
    euro
    -3.69
     Danish
    -3.64
     HK
    -3.63
    EU
    -3.62
     Dota
    -3.58
     Copenhagen
    -3.57
    POSITIVE LOGITS
     Mississippi
    8.58
     Hatt
    6.39
     Arkansas
    6.08
     Louisiana
    5.59
     Alabama
    5.50
     Sioux
    5.41
     Tennessee
    5.40
    ippi
    5.37
    Alabama
    5.32
     Missouri
    5.19
    Activations Density 0.006%

    No Known Activations