© 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. 10-ATT-KK
    11. 23030
    Prev
    Next
    INDEX
    Explanations

    references to DACA (Deferred Action for Childhood Arrivals) and related immigration issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.21
    1:0.03
    2:0.04
    3:0.08
    4:0.06
    5:0.02
    6:0.16
    7:0.12
    8:0.01
    9:0.05
    10:0.13
    11:0.05
    Negative Logits
     Ramsay
    -3.44
    Gordon
    -3.43
     whisky
    -3.24
     Gordon
    -3.15
    nit
    -3.00
     Notting
    -2.94
     cannibal
    -2.92
     Gaddafi
    -2.90
     Leone
    -2.90
    agara
    -2.90
    POSITIVE LOGITS
     DACA
    8.64
     deportation
    4.71
     deport
    4.54
    REAM
    4.46
     deported
    4.06
    Dream
    4.06
     Dream
    4.03
    ctuary
    3.94
     DHS
    3.91
    ACA
    3.87
    Activations Density 0.020%

    No Known Activations