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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14686
    Prev
    Next
    INDEX
    Explanations

    mentions and attributions related to individuals, particularly in political contexts

    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
    0:0.09
    1:0.02
    2:0.08
    3:0.04
    4:0.03
    5:0.04
    6:0.29
    7:0.03
    8:0.05
    9:0.23
    10:0.02
    11:0.02
    Negative Logits
     germ
    -4.22
    anto
    -3.85
    Dom
    -3.70
    ��
    -3.66
     Som
    -3.63
     Tsuk
    -3.57
    imei
    -3.51
     dom
    -3.49
     Zimmer
    -3.48
     incorpor
    -3.37
    POSITIVE LOGITS
     Burn
    10.13
    Burn
    9.64
     Burns
    9.13
     burn
    8.56
    burn
    8.16
     Burning
    7.22
     burned
    7.20
     burns
    7.20
    burning
    7.11
     burning
    6.71
    Activations Density 0.012%

    No Known Activations