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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 11972
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and humanitarian issues, including human rights, victims of exploitation, and international agreements

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.33
    2:0.04
    3:0.05
    4:0.03
    5:0.04
    6:0.06
    7:0.07
    8:0.04
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
     Edison
    -2.45
    Graph
    -2.36
    DonaldTrump
    -2.29
     Neural
    -2.28
    Beast
    -2.27
    lectic
    -2.25
    ultimate
    -2.21
     Pinball
    -2.19
    ellow
    -2.18
    Brew
    -2.18
    POSITIVE LOGITS
     Sudan
    3.18
     NGOs
    3.16
     NGO
    3.03
     Rohingya
    3.01
     detention
    2.92
     Rwanda
    2.81
     Erit
    2.79
     migrant
    2.76
     paramilitary
    2.75
     UNHCR
    2.72
    Activations Density 0.399%

    No Known Activations