© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    instances of significant events and actions related to authority figures

    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
    1:0.09
    2:0.06
    3:0.03
    4:0.05
    5:0.03
    6:0.16
    7:0.05
    8:0.05
    9:0.28
    10:0.03
    11:0.04
    Negative Logits
    ogg
    -3.26
    yip
    -3.18
    vern
    -3.16
     appliance
    -3.14
    mo
    -3.14
     pouch
    -3.03
     sulph
    -2.98
    OG
    -2.97
    giene
    -2.96
    Roger
    -2.95
    POSITIVE LOGITS
     Has
    4.70
     Had
    4.30
    Has
    3.88
     Hass
    3.86
     Hes
    3.80
     Hath
    3.79
    Had
    3.75
     Accord
    3.64
     Claims
    3.57
     Att
    3.45
    Activations Density 0.001%

    No Known Activations