© 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. 19364
    Prev
    Next
    INDEX
    Explanations

    common themes of protest and social activism

    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
    0:0.05
    1:0.02
    2:0.07
    3:0.05
    4:0.03
    5:0.06
    6:0.05
    7:0.03
    8:0.45
    9:0.07
    10:0.03
    11:0.05
    Negative Logits
     JFK
    -4.84
     Gotham
    -4.22
     Manhattan
    -4.11
     Palest
    -4.04
    hattan
    -3.76
     NYPD
    -3.66
    Philadelphia
    -3.65
     Hernandez
    -3.63
     Kessler
    -3.49
     Mets
    -3.48
    POSITIVE LOGITS
     Saskatchewan
    9.10
     Sask
    8.83
     Regina
    6.89
     Manitoba
    6.31
     Winnipeg
    6.01
    atchewan
    5.64
     provincial
    5.59
     Aboriginal
    5.52
     Edmonton
    5.49
     province
    5.20
    Activations Density 0.014%

    No Known Activations