© 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. 10713
    Prev
    Next
    INDEX
    Explanations

    references to significant geopolitical events and 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
    0:0.43
    1:0.01
    2:0.12
    3:0.10
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.06
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
    Wisconsin
    -2.47
    Origin
    -2.41
    Denver
    -2.33
    Toronto
    -2.31
    Seattle
    -2.23
    Mexico
    -2.17
    Chicago
    -2.16
    alore
    -2.11
    eus
    -2.09
    Michigan
    -2.06
    POSITIVE LOGITS
     population
    2.53
     Unemployment
    2.51
    population
    2.26
     inhabitants
    2.13
     reun
    2.12
     harbor
    2.09
     unemployment
    2.05
     thriving
    1.98
     democratically
    1.96
     Communism
    1.95
    Activations Density 1.256%

    No Known Activations