© 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. 9747
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to political and social controversy

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.11
    4:0.03
    5:0.07
    6:0.14
    7:0.04
    8:0.03
    9:0.03
    10:0.10
    11:0.31
    Negative Logits
     Stream
    -2.47
     Boots
    -2.41
     fucking
    -2.40
     JD
    -2.40
     River
    -2.34
     Wine
    -2.32
     Pocket
    -2.31
     Pump
    -2.31
     BM
    -2.31
     "$:/
    -2.28
    POSITIVE LOGITS
    polit
    2.92
    ADVERTISEMENT
    2.79
    ItemImage
    2.79
    rosso
    2.78
     (@
    2.75
    fal
    2.73
    /?
    2.73
    pic
    2.69
    tom
    2.63
    Apr
    2.63
    Activations Density 0.006%

    No Known Activations