© 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. 18811
    Prev
    Next
    INDEX
    Explanations

    terms related to political party dynamics and legislative processes

    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
    1:0.03
    2:0.11
    3:0.11
    4:0.05
    5:0.12
    6:0.04
    7:0.11
    8:0.11
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    natureconservancy
    -2.51
     Elon
    -2.49
    advertisement
    -2.45
     Gareth
    -2.36
    areth
    -2.23
     trolls
    -2.21
    Gaza
    -2.19
     troll
    -2.19
     Damon
    -2.16
     ★
    -2.12
    POSITIVE LOGITS
     Confederation
    3.27
     Quebec
    3.22
     Provincial
    3.15
     Qué
    3.14
     amalg
    3.13
     1901
    3.00
     feder
    2.82
     provinces
    2.78
     Manitoba
    2.77
     1912
    2.75
    Activations Density 0.036%

    No Known Activations