© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21992
    Prev
    Next
    INDEX
    Explanations

    terms related to white supremacy and nationalist movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.05
    2:0.15
    3:0.06
    4:0.05
    5:0.09
    6:0.04
    7:0.05
    8:0.05
    9:0.19
    10:0.10
    11:0.04
    Negative Logits
    isSpecialOrderable
    -1.22
    croft
    -1.14
    udget
    -1.07
    bender
    -1.06
    ivable
    -1.06
     drawback
    -1.06
     Strait
    -1.05
     adjustment
    -1.03
    channelAvailability
    -1.02
    EVA
    -1.01
    POSITIVE LOGITS
     KKK
    1.20
     Gathering
    1.14
     crucifix
    1.11
    hirt
    1.08
     pedoph
    1.06
     Klan
    1.04
     whom
    1.04
     Gleaming
    1.03
     marching
    1.02
    aces
    1.01
    Activations Density 0.007%

    No Known Activations