© 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. 2-ATT-KK
    11. 11589
    Prev
    Next
    INDEX
    Explanations

    mentions of political and legal issues related to immigration and refugees

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.20
    3:0.05
    4:0.11
    5:0.08
    6:0.03
    7:0.05
    8:0.05
    9:0.20
    10:0.08
    11:0.03
    Negative Logits
    機
    -1.25
    将
    -1.18
    ヴァ
    -1.16
    Browser
    -1.15
    ��
    -1.14
     antitrust
    -1.12
    ヤ
    -1.12
     modification
    -1.10
    FOX
    -1.09
     magnification
    -1.09
    POSITIVE LOGITS
    isconsin
    1.50
    anwhile
    1.42
     Kuwait
    1.33
    owship
    1.30
     fleeing
    1.29
     Estonia
    1.26
    abwe
    1.25
     Uganda
    1.20
     Ethiopia
    1.19
    ufact
    1.19
    Activations Density 0.014%

    No Known Activations