© 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. 3-ATT-KK
    11. 13585
    Prev
    Next
    INDEX
    Explanations

    words related to controversial statements, criticism, and political events and figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements or remarks made by individuals in a political or controversial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.07
    3:0.07
    4:0.02
    5:0.07
    6:0.07
    7:0.32
    8:0.08
    9:0.07
    10:0.07
    11:0.07
    Negative Logits
    FTWARE
    -1.26
     Yug
    -1.24
     Devi
    -1.18
     Shant
    -1.12
     CY
    -1.08
     Asset
    -1.08
     Tycoon
    -1.07
     Zed
    -1.04
    rients
    -0.99
    utical
    -0.99
    POSITIVE LOGITS
     louder
    1.45
     uttered
    1.44
     aloud
    1.29
    rompt
    1.26
     omission
    1.24
    noxious
    1.21
     speeches
    1.18
     loudly
    1.15
     sarcast
    1.13
    plain
    1.13
    Activations Density 0.042%

    No Known Activations