© 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. 19511
    Prev
    Next
    INDEX
    Explanations

    statements pertaining to public figures and their opinions or actions

    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
    3:0.04
    4:0.04
    5:0.04
    6:0.16
    7:0.03
    8:0.08
    9:0.38
    10:0.02
    11:0.03
    Negative Logits
    黒
    -4.40
     Kis
    -4.21
     Kush
    -3.96
    Lew
    -3.94
     Gork
    -3.84
    Els
    -3.72
     Lew
    -3.48
    iza
    -3.35
     Kaf
    -3.30
     gir
    -3.30
    POSITIVE LOGITS
     Patrick
    9.38
    Patrick
    8.67
    patrick
    6.47
     Pat
    5.62
     PAT
    5.47
    Pat
    4.97
     Patty
    4.53
     Patt
    4.16
    ATHER
    4.16
     Cath
    4.15
    Activations Density 0.007%

    No Known Activations