© 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. 3-ATT-KK
    11. 11749
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement activities and personnel

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of police officers and law enforcement personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.35
    1:0.04
    2:0.07
    3:0.03
    4:0.09
    5:0.06
    6:0.09
    7:0.06
    8:0.03
    9:0.02
    10:0.09
    11:0.04
    Negative Logits
    etus
    -1.62
     wheat
    -1.38
    peat
    -1.34
    Tea
    -1.33
    tern
    -1.31
     cake
    -1.29
    append
    -1.27
     barley
    -1.26
    empl
    -1.24
     unification
    -1.23
    POSITIVE LOGITS
     discharged
    1.73
     examiner
    1.64
     Operations
    1.61
     personnel
    1.59
     helicop
    1.54
     Officers
    1.53
    intendent
    1.53
     Dept
    1.52
     investigator
    1.50
     dispatched
    1.50
    Activations Density 0.097%

    No Known Activations