© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 19963
    Prev
    Next
    INDEX
    Explanations

    events involving crime and suspicious behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.05
    2:0.05
    3:0.10
    4:0.08
    5:0.03
    6:0.07
    7:0.16
    8:0.03
    9:0.05
    10:0.10
    11:0.11
    Negative Logits
    oppable
    -2.74
     Liberia
    -2.45
     UKIP
    -2.41
    Room
    -2.38
     Bunker
    -2.38
     homelessness
    -2.37
     Olsen
    -2.37
     Guards
    -2.35
    oyer
    -2.34
     Maryland
    -2.34
    POSITIVE LOGITS
     Ved
    4.64
     Sanskrit
    4.32
     Zar
    4.07
     Bh
    3.92
     Yug
    3.90
     Brah
    3.77
     Mazda
    3.75
     Vish
    3.55
     Rak
    3.52
    ashtra
    3.48
    Activations Density 0.004%

    No Known Activations