© 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 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. 13457
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial decisions

    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
    0:0.04
    1:0.01
    2:0.05
    3:0.09
    4:0.02
    5:0.06
    6:0.03
    7:0.04
    8:0.55
    9:0.02
    10:0.02
    11:0.02
    Negative Logits
    NetMessage
    -3.68
     Runes
    -3.50
    Kent
    -3.48
    wolves
    -3.35
     Glou
    -3.31
    orkshire
    -3.24
     sled
    -3.18
     Ukip
    -3.14
     Somerset
    -3.13
    verett
    -3.06
    POSITIVE LOGITS
     Colombian
    7.88
     Mexican
    7.66
     Argentine
    7.63
     Venezuelan
    7.45
     Spanish
    7.45
     Guatem
    7.40
    Mexico
    7.40
    Spanish
    7.28
     Honduras
    7.22
     Chilean
    7.21
    Activations Density 1.365%

    No Known Activations