© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 745
    Prev
    Next
    INDEX
    Explanations

    references to legal matters or judicial concepts

    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
    0:0.06
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.05
    6:0.24
    7:0.05
    8:0.04
    9:0.29
    10:0.02
    11:0.05
    Negative Logits
     Xu
    -4.61
     ASC
    -4.22
     SQ
    -4.00
     EPS
    -3.62
     prote
    -3.57
     Khe
    -3.56
     Qin
    -3.49
    actionDate
    -3.46
     ultras
    -3.44
    20439
    -3.44
    POSITIVE LOGITS
     Marshall
    10.83
    Marsh
    10.18
     Marsh
    6.88
     Marshal
    6.47
     marsh
    5.88
     Cutler
    4.63
    Forest
    4.24
     Butler
    4.21
    arsh
    4.17
     Forrest
    3.95
    Activations Density 0.006%

    No Known Activations