© 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 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. 803
    Prev
    Next
    INDEX
    Explanations

    references to public safety systems or initiatives

    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
    0:0.11
    1:0.03
    2:0.10
    3:0.06
    4:0.09
    5:0.06
    6:0.13
    7:0.05
    8:0.17
    9:0.10
    10:0.03
    11:0.03
    Negative Logits
     Hunts
    -3.79
     Hawkins
    -3.72
     Savage
    -3.57
     Spears
    -3.56
     Drift
    -3.35
     Sutherland
    -3.23
     McGregor
    -3.16
     Clan
    -3.16
    Thunder
    -3.12
     TCU
    -3.10
    POSITIVE LOGITS
     PB
    7.26
     MTA
    7.23
    PB
    5.82
     FD
    5.32
     Cuomo
    4.98
     NYPD
    4.54
     NYC
    4.50
    NY
    4.49
     borough
    4.39
     Bronx
    4.30
    Activations Density 0.003%

    No Known Activations