© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11582
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating political and social issues, particularly regarding governance and public welfare

    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
    1:0.48
    2:0.06
    3:0.02
    4:0.03
    5:0.05
    6:0.04
    7:0.04
    8:0.04
    9:0.03
    10:0.06
    11:0.09
    Negative Logits
    itivity
    -1.52
    ongyang
    -1.52
    anmar
    -1.43
    ramid
    -1.43
    ielding
    -1.42
    iosyncr
    -1.39
    rero
    -1.39
    merce
    -1.39
    adena
    -1.38
     condem
    -1.36
    POSITIVE LOGITS
    ‑
    1.73
     or
    1.71
    テ
    1.61
    }
    1.59
    】
    1.58
     nor
    1.51
    |
    1.51
    ファ
    1.49
    ★★
    1.48
    ](
    1.39
    Activations Density 0.110%

    No Known Activations