© 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. 9921
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with fame and celebrity culture

    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
    0:0.35
    1:0.01
    2:0.14
    3:0.10
    4:0.10
    5:0.05
    6:0.04
    7:0.07
    8:0.01
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
     Rhodes
    -4.21
     Chandler
    -4.21
     rye
    -3.98
     pigeon
    -3.78
     Tyson
    -3.60
     KC
    -3.46
     torpedo
    -3.37
     smoker
    -3.33
     flies
    -3.30
     Hughes
    -3.23
    POSITIVE LOGITS
     �
    8.01
    �
    7.04
    †
    5.13
    �
    4.66
    ¶
    4.34
    ─
    4.33
    ‎
    4.32
    ═
    3.96
    soType
    3.96
    �
    3.96
    Activations Density 4.024%

    No Known Activations