© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and government activity

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

    names of politicians and their affiliations

    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
    1:0.35
    2:0.06
    3:0.03
    4:0.03
    5:0.04
    6:0.07
    7:0.07
    8:0.05
    9:0.04
    10:0.06
    11:0.14
    Negative Logits
    ijn
    -1.80
    Reviewer
    -1.77
    alys
    -1.65
    DragonMagazine
    -1.59
    』
    -1.45
    idges
    -1.41
    atonin
    -1.37
    rats
    -1.36
    ampires
    -1.34
    artifacts
    -1.34
    POSITIVE LOGITS
     Corker
    1.93
     Republican
    1.67
    Republican
    1.59
     Capitol
    1.56
    Senate
    1.54
    CNN
    1.53
    aucus
    1.50
     Congressional
    1.47
     Senate
    1.47
     congressional
    1.46
    Activations Density 0.043%

    No Known Activations