© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10602
    Prev
    Next
    INDEX
    Explanations

    elements related to law enforcement actions and reports

    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
    0:0.03
    1:0.05
    2:0.13
    3:0.03
    4:0.06
    5:0.05
    6:0.21
    7:0.18
    8:0.07
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
    obyl
    -1.16
    ヘ
    -1.15
     Mankind
    -1.13
    akespeare
    -1.10
    ines
    -1.09
    oliberal
    -1.08
    inary
    -1.08
    ankind
    -1.07
     humankind
    -1.04
     Spir
    -1.02
    POSITIVE LOGITS
     lookout
    1.34
    ijah
    1.32
     htt
    1.23
     suspic
    1.20
    Officers
    1.18
     ATF
    1.15
     handcuffs
    1.14
     RH
    1.13
    enhagen
    1.09
    !'"
    1.09
    Activations Density 0.071%

    No Known Activations