© 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. 21502
    Prev
    Next
    INDEX
    Explanations

    references to social activism and protests

    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
    0:0.24
    1:0.04
    2:0.04
    3:0.04
    4:0.03
    5:0.03
    6:0.13
    7:0.15
    8:0.01
    9:0.05
    10:0.14
    11:0.04
    Negative Logits
     bour
    -3.58
     Lisbon
    -3.44
     Dracula
    -3.38
     Bam
    -3.27
     Tripoli
    -3.25
     Mirage
    -3.21
     Nash
    -3.21
     Drac
    -3.17
     Hitchcock
    -3.12
     Lyme
    -3.05
    POSITIVE LOGITS
     Kaepernick
    7.91
    aepernick
    6.25
    bleacher
    4.66
     kneeling
    4.58
    NFL
    4.48
     kne
    4.12
    aeper
    3.98
     Colin
    3.88
     NFL
    3.85
     Seahawks
    3.68
    Activations Density 0.006%

    No Known Activations