© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18599
    Prev
    Next
    INDEX
    Explanations

    references to arrests and law enforcement-related activities

    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
    1:0.17
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.17
    7:0.03
    8:0.03
    9:0.26
    10:0.05
    11:0.03
    Negative Logits
    anches
    -3.69
     Harper
    -3.36
    isters
    -3.35
    hall
    -3.15
    bern
    -3.08
    dden
    -3.07
    Bern
    -3.05
    Blocks
    -3.05
    illard
    -3.04
     Barcl
    -3.02
    POSITIVE LOGITS
    SO
    6.57
     SO
    6.37
     SOS
    5.58
    so
    4.43
     Sole
    4.13
    oso
    3.88
     streng
    3.84
     Sapp
    3.83
     PSP
    3.82
     Sao
    3.76
    Activations Density 0.002%

    No Known Activations