© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14876
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal testimony and judicial proceedings

    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
    0:0.04
    1:0.06
    2:0.06
    3:0.04
    4:0.04
    5:0.01
    6:0.06
    7:0.07
    8:0.02
    9:0.03
    10:0.47
    11:0.04
    Negative Logits
    inki
    -3.16
    ê
    -3.05
    ELY
    -3.04
     EL
    -3.03
     Kel
    -2.98
     el
    -2.96
     Kelvin
    -2.93
    edi
    -2.88
    elin
    -2.81
    EVA
    -2.78
    POSITIVE LOGITS
     Sc
    10.52
    Sc
    9.35
    sc
    8.05
     sc
    7.93
     SC
    6.38
     Scrib
    5.54
    SC
    5.19
     Scorp
    4.86
     scr
    4.83
     Scala
    4.62
    Activations Density 0.091%

    No Known Activations