© 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. 11907
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and specific event details

    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
    2:0.05
    3:0.04
    4:0.05
    5:0.04
    6:0.24
    7:0.06
    8:0.06
    9:0.24
    10:0.02
    11:0.05
    Negative Logits
     debugger
    -3.42
     Cunningham
    -3.28
     whistlebl
    -3.24
     Debug
    -3.17
     Otto
    -3.06
     Reaper
    -3.06
     scaff
    -3.00
     intercept
    -2.92
     Pilot
    -2.90
     ogre
    -2.90
    POSITIVE LOGITS
    Las
    8.98
     Las
    8.78
     Vegas
    7.29
     las
    5.30
    las
    5.18
     MGM
    5.13
    Nev
    5.06
    LV
    4.89
     NRS
    4.73
     Nevada
    4.67
    Activations Density 0.007%

    No Known Activations