© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 16820
    Prev
    Next
    INDEX
    Explanations

    references to immigration and deportation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.05
    4:0.13
    5:0.03
    6:0.02
    7:0.36
    8:0.02
    9:0.03
    10:0.13
    11:0.08
    Negative Logits
    natureconservancy
    -2.02
    Dialog
    -1.68
    swers
    -1.53
    Reviewer
    -1.44
     viewership
    -1.44
    �
    -1.44
     podium
    -1.43
    Panel
    -1.41
    uten
    -1.41
     airs
    -1.39
    POSITIVE LOGITS
     Rohingya
    1.69
     Pakistani
    1.68
     Luxem
    1.65
     Uzbek
    1.63
     Erit
    1.62
     refugees
    1.57
     Pakistan
    1.56
    lyak
    1.54
     Bangladesh
    1.52
     deported
    1.49
    Activations Density 0.002%

    No Known Activations