© 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. 19014
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations or landmarks

    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
    2:0.02
    3:0.19
    4:0.02
    5:0.10
    6:0.07
    7:0.02
    8:0.11
    9:0.27
    10:0.03
    11:0.03
    Negative Logits
     mathemat
    -3.33
     Cipher
    -3.09
     Tid
    -3.02
     bunk
    -3.02
     NBN
    -2.99
     Atomic
    -2.94
     Pesh
    -2.87
    �
    -2.85
     Ic
    -2.82
     timet
    -2.77
    POSITIVE LOGITS
    Louis
    5.25
     Louis
    5.19
     STL
    3.94
     Saints
    3.90
     Louie
    3.79
    Lou
    3.64
     Missouri
    3.58
     Claude
    3.54
    Luc
    3.51
    Saint
    3.51
    Activations Density 0.001%

    No Known Activations