Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11373
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and relationships between countries

    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
    1:0.03
    2:0.07
    3:0.04
    4:0.07
    5:0.04
    6:0.23
    7:0.06
    8:0.08
    9:0.20
    10:0.02
    11:0.05
    Negative Logits
    Ford
    -4.05
     Ford
    -3.73
    charg
    -3.69
     lantern
    -3.59
    Hay
    -3.43
     Hud
    -3.38
     hous
    -3.24
     McKenzie
    -3.21
     comet
    -3.19
     emit
    -3.13
    POSITIVE LOGITS
     Serbia
    8.60
     Serbian
    8.01
     Yugoslavia
    6.14
     Kosovo
    6.12
     Alban
    6.04
     Balkans
    5.92
     Macedonia
    5.84
     Albania
    5.53
     Croatia
    5.51
     Yugoslav
    5.48
    Activations Density 0.005%

    No Known Activations