Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10626
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration policies and regulations

    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
    1:0.01
    2:0.20
    3:0.07
    4:0.02
    5:0.07
    6:0.04
    7:0.05
    8:0.37
    9:0.03
    10:0.02
    11:0.01
    Negative Logits
     Pistons
    -3.39
     VK
    -3.30
     bour
    -3.28
     Nich
    -3.14
    ombat
    -3.09
    obyl
    -3.09
     Olympus
    -3.07
    NetMessage
    -3.07
    nit
    -3.05
     Fou
    -3.00
    POSITIVE LOGITS
     DACA
    7.54
     immigration
    7.21
     Mexican
    7.15
     Immigration
    7.14
    Mex
    6.94
     deport
    6.87
     immigrant
    6.80
     Mexicans
    6.79
     deportation
    6.71
     deported
    6.69
    Activations Density 0.372%

    No Known Activations