© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    mentions of political candidates and their titles within the context of elections

    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
    0:0.03
    1:0.01
    2:0.14
    3:0.09
    4:0.05
    5:0.03
    6:0.05
    7:0.08
    8:0.05
    9:0.04
    10:0.23
    11:0.15
    Negative Logits
    Rated
    -1.42
     specialize
    -1.38
     respons
    -1.38
     Ples
    -1.31
     lux
    -1.28
     gou
    -1.28
     vulner
    -1.27
     multiplier
    -1.26
    pload
    -1.26
     bottleneck
    -1.22
    POSITIVE LOGITS
     Everett
    1.39
     Briggs
    1.38
     Fallon
    1.37
     Harding
    1.36
    etti
    1.35
    ��士
    1.33
     Alberto
    1.33
    ogan
    1.32
    remlin
    1.30
     Adolf
    1.28
    Activations Density 0.030%

    No Known Activations