© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    mentions of police violence and racial issues in the context of specific 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
    0:0.15
    1:0.01
    2:0.21
    3:0.07
    4:0.03
    5:0.06
    6:0.04
    7:0.07
    8:0.23
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     Zoro
    -4.03
    Japan
    -3.34
     Mermaid
    -3.23
    ertility
    -3.22
     HM
    -3.14
     Yoshi
    -3.13
     horm
    -3.12
     Drac
    -3.10
     spa
    -3.07
     Scy
    -3.02
    POSITIVE LOGITS
     Ferguson
    6.65
     Darren
    4.71
    erguson
    4.71
     Trayvon
    4.30
     riots
    4.05
     Garner
    4.03
     protests
    3.62
     NAACP
    3.56
     Missouri
    3.55
     looting
    3.42
    Activations Density 0.021%

    No Known Activations