© 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. 8067
    Prev
    Next
    INDEX
    Explanations

    instances of power dynamics and authority in social and political contexts

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.03
    4:0.07
    5:0.03
    6:0.04
    7:0.07
    8:0.02
    9:0.16
    10:0.03
    11:0.41
    Negative Logits
    stories
    -3.11
     beers
    -3.08
    cases
    -3.05
     salads
    -2.88
     summers
    -2.88
     lifestyles
    -2.87
     layouts
    -2.86
     diets
    -2.85
     styles
    -2.80
     experiences
    -2.77
    POSITIVE LOGITS
     regulator
    3.93
     intermediary
    3.86
     protector
    3.51
     watchdog
    3.50
    ensor
    3.32
     entity
    3.25
     source
    3.24
    agent
    3.23
     arbit
    3.21
     ally
    3.17
    Activations Density 0.159%

    No Known Activations