© 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. 6839
    Prev
    Next
    INDEX
    Explanations

    content related to events and actions relating to law enforcement or related incidents

    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
    0:0.04
    1:0.03
    2:0.10
    3:0.28
    4:0.04
    5:0.04
    6:0.03
    7:0.05
    8:0.23
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
    ization
    -2.92
     stabilization
    -2.86
    imize
    -2.71
     normalized
    -2.67
     behaviors
    -2.66
    Footnote
    -2.56
     §
    -2.56
     [[
    -2.54
     ≥
    -2.51
     baseline
    -2.46
    POSITIVE LOGITS
     Cardiff
    3.78
     footballer
    3.65
     £
    3.64
     Ukip
    3.40
     Manchester
    3.35
    ffield
    3.35
    Manchester
    3.27
     Glasgow
    3.23
     Wembley
    3.20
    Liverpool
    3.18
    Activations Density 0.015%

    No Known Activations