© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 10053
    Prev
    Next
    INDEX
    Explanations

    references to police activity and their operational conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.03
    3:0.04
    4:0.02
    5:0.04
    6:0.02
    7:0.03
    8:0.02
    9:0.06
    10:0.52
    11:0.14
    Negative Logits
    thereum
    -1.76
    rencies
    -1.67
    lag
    -1.54
    weet
    -1.47
    ────
    -1.43
     currencies
    -1.35
    egg
    -1.35
     symmetry
    -1.34
    iquid
    -1.33
    Brazil
    -1.32
    POSITIVE LOGITS
     patrols
    2.48
     patrolling
    2.48
     patrol
    2.29
     Patrol
    2.27
     Detect
    2.06
    intendent
    2.04
     Sergeant
    2.01
     Officers
    2.00
     Constable
    1.99
     investigating
    1.99
    Activations Density 1.601%

    No Known Activations