© 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. 22141
    Prev
    Next
    INDEX
    Explanations

    content related to political statements and government actions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    1:0.16
    2:0.04
    3:0.04
    4:0.02
    5:0.05
    6:0.10
    7:0.11
    8:0.03
    9:0.04
    10:0.21
    11:0.09
    Negative Logits
    etsy
    -1.33
     someday
    -1.29
    Favorite
    -1.27
    ��
    -1.25
    Kids
    -1.24
     Lovecraft
    -1.23
     Glow
    -1.22
    ||||
    -1.21
     NYC
    -1.21
    gravity
    -1.20
    POSITIVE LOGITS
     ceasefire
    1.76
     Kazakh
    1.68
     Ankara
    1.67
     Erdogan
    1.66
     Abbas
    1.66
     Rohingya
    1.64
     Lavrov
    1.64
     Nato
    1.63
     Tayyip
    1.61
     Sudan
    1.60
    Activations Density 1.127%

    No Known Activations