© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    names of locations and specific geographic references

    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
    1:0.02
    2:0.04
    3:0.35
    4:0.03
    5:0.07
    6:0.02
    7:0.06
    8:0.18
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     peanuts
    -2.53
     Kush
    -2.34
     Torch
    -2.34
     bats
    -2.27
     Kaepernick
    -2.18
     bitcoins
    -2.18
     Skull
    -2.17
     Mormonism
    -2.17
     misplaced
    -2.16
     trolls
    -2.15
    POSITIVE LOGITS
    ère
    5.09
    ét
    4.87
    è
    4.54
    é
    4.38
     Franç
    4.18
    France
    4.04
     É
    3.97
    ité
    3.95
    É
    3.93
    Paris
    3.93
    Activations Density 0.065%

    No Known Activations