© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 262
    Prev
    Next
    INDEX
    Explanations

    references to political figures and human rights 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
    0:0.08
    1:0.02
    2:0.09
    3:0.06
    4:0.02
    5:0.05
    6:0.08
    7:0.05
    8:0.35
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
     Blackhawks
    -4.33
     Ballard
    -4.29
     Calgary
    -4.00
     Spokane
    -3.86
     puck
    -3.69
     Shanahan
    -3.68
     Pike
    -3.63
    Chicago
    -3.54
     Anaheim
    -3.43
     Vancouver
    -3.42
    POSITIVE LOGITS
     Tunis
    10.07
     Tunisia
    9.26
     Moroccan
    6.42
     Algeria
    6.11
     Morocco
    6.00
     Tripoli
    5.85
     Maurit
    5.71
     Lebanese
    5.69
     Beirut
    5.32
     Alger
    5.32
    Activations Density 0.008%

    No Known Activations