© 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. 12416
    Prev
    Next
    INDEX
    Explanations

    references to police actions and 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
    0:0.40
    1:0.01
    2:0.17
    3:0.11
    4:0.02
    5:0.07
    6:0.01
    7:0.04
    8:0.05
    9:0.01
    10:0.04
    11:0.01
    Negative Logits
     Publishers
    -3.09
    olkien
    -2.61
     Publisher
    -2.43
     publisher
    -2.41
     projector
    -2.39
     Authors
    -2.37
     Univ
    -2.31
    Publisher
    -2.25
     Civilization
    -2.25
     Zot
    -2.22
    POSITIVE LOGITS
     patrolling
    4.05
     patrol
    3.79
     patrols
    3.74
    Officers
    3.44
     officers
    3.33
     uniforms
    3.26
     duty
    3.13
     investigating
    3.11
     arresting
    3.09
     Officers
    3.00
    Activations Density 1.012%

    No Known Activations