© 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. 22640
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, government, and policies

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

    mentions of the word "enemy" and its related context

    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
    0:0.04
    1:0.03
    2:0.15
    3:0.04
    4:0.36
    5:0.03
    6:0.04
    7:0.02
    8:0.07
    9:0.10
    10:0.04
    11:0.02
    Negative Logits
    throp
    -1.52
     anecd
    -1.49
    Guard
    -1.45
    abo
    -1.44
    aqu
    -1.39
    Zip
    -1.38
    rek
    -1.37
    Stock
    -1.36
    quad
    -1.36
    rh
    -1.36
    POSITIVE LOGITS
    ドラ
    1.53
     Confeder
    1.42
     Mormonism
    1.36
     Brotherhood
    1.35
     Axis
    1.34
    terness
    1.31
    ドラゴン
    1.29
     Hearts
    1.27
     Ferdinand
    1.25
     prejudice
    1.24
    Activations Density 0.008%

    No Known Activations