© 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. 9-ATT-KK
    11. 23802
    Prev
    Next
    INDEX
    Explanations

    mentions of legal issues and criminal allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.02
    2:0.21
    3:0.09
    4:0.03
    5:0.09
    6:0.02
    7:0.06
    8:0.15
    9:0.02
    10:0.05
    11:0.03
    Negative Logits
     Coyotes
    -2.94
     forestry
    -2.84
    ignty
    -2.79
     Indigenous
    -2.73
     shortages
    -2.62
     Aboriginal
    -2.57
     Agric
    -2.55
     Plant
    -2.53
    requisite
    -2.51
     Hurricanes
    -2.51
    POSITIVE LOGITS
     Weiner
    6.15
     Abedin
    4.24
     Huma
    4.01
     lewd
    3.55
     texting
    3.35
     masturb
    3.34
    ileaks
    3.18
     pedoph
    3.13
     Craigslist
    3.02
     ejac
    2.98
    Activations Density 0.008%

    No Known Activations