© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    references to criminal behavior involving minors

    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
    0:0.08
    1:0.09
    2:0.17
    3:0.07
    4:0.08
    5:0.02
    6:0.09
    7:0.15
    8:0.03
    9:0.04
    10:0.05
    11:0.08
    Negative Logits
    nir
    -2.48
    zbollah
    -2.31
    ptin
    -2.25
     [|
    -2.24
    Exit
    -2.19
    idates
    -2.15
    atra
    -2.11
    irs
    -2.06
    �
    -2.06
    ゴン
    -2.06
    POSITIVE LOGITS
     Grade
    3.32
     teenager
    3.11
     boy
    2.99
     underage
    2.96
     14
    2.95
     kinderg
    2.94
     toddler
    2.90
     16
    2.87
     teen
    2.86
     girl
    2.85
    Activations Density 0.124%

    No Known Activations