© 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. 9-ATT-KK
    11. 4058
    Prev
    Next
    INDEX
    Explanations

    references to social and political activism, particularly related to issues of race and immigration

    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
    0:0.06
    1:0.02
    2:0.08
    3:0.07
    4:0.05
    5:0.08
    6:0.11
    7:0.05
    8:0.26
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
     Bolt
    -4.10
     Pegasus
    -3.80
     Falk
    -3.65
     Rove
    -3.47
    merga
    -3.46
     Rover
    -3.38
     »
    -3.37
     MPG
    -3.35
     Slovenia
    -3.35
     Norway
    -3.35
    POSITIVE LOGITS
     Chinatown
    10.00
    atown
    5.86
     Chinese
    5.49
    Chinese
    5.37
     Chow
    5.09
     Taiwanese
    5.02
     Filipino
    4.96
     Chan
    4.92
     Chao
    4.90
     Vietnamese
    4.84
    Activations Density 0.001%

    No Known Activations