© 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. 5-ATT-KK
    11. 3302
    Prev
    Next
    INDEX
    Explanations

    references to political actions and statements surrounding elections and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.08
    3:0.09
    4:0.03
    5:0.10
    6:0.03
    7:0.04
    8:0.06
    9:0.14
    10:0.14
    11:0.16
    Negative Logits
     independ
    -1.00
    inav
    -0.96
     avail
    -0.94
    riv
    -0.93
    lite
    -0.90
     attain
    -0.89
     *.
    -0.88
     flavour
    -0.86
    lease
    -0.85
    inction
    -0.84
    POSITIVE LOGITS
     HuffPost
    1.17
     Called
    1.14
    Morning
    1.11
     "@
    1.02
     Asked
    1.00
     Palest
    1.00
     Klux
    0.99
    ccording
    0.95
     Stab
    0.94
     Amid
    0.94
    Activations Density 0.266%

    No Known Activations