© 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. 10-ATT-KK
    11. 14124
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions involving conflict or confrontation

    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
    0:0.16
    1:0.07
    2:0.05
    3:0.05
    4:0.05
    5:0.02
    6:0.06
    7:0.23
    8:0.01
    9:0.04
    10:0.08
    11:0.13
    Negative Logits
     Latvia
    -2.12
    Mouse
    -2.11
     Wilde
    -2.10
     Lithuania
    -2.06
    ère
    -2.02
    ipation
    -1.91
     Booth
    -1.88
     Rabbit
    -1.88
     Romania
    -1.83
     diaper
    -1.79
    POSITIVE LOGITS
     rocks
    3.67
     bould
    3.66
     Rocks
    3.17
     lava
    2.81
     boulder
    2.76
     granite
    2.70
     cliffs
    2.70
     fossils
    2.68
     asteroids
    2.68
     minerals
    2.60
    Activations Density 0.044%

    No Known Activations