Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14639
    Prev
    Next
    INDEX
    Explanations

    political affiliations and preferences among different groups of people, particularly regarding the Democratic and Republican parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.09
    2:0.05
    3:0.06
    4:0.04
    5:0.02
    6:0.11
    7:0.28
    8:0.02
    9:0.05
    10:0.04
    11:0.11
    Negative Logits
     Adidas
    -2.50
     barracks
    -2.40
     Breast
    -2.31
     Engineer
    -2.23
     Refugees
    -2.12
     breasts
    -2.07
     Sochi
    -2.06
     ordinance
    -2.06
     ancestor
    -2.05
     td
    -2.03
    POSITIVE LOGITS
    crim
    2.52
    leans
    2.35
    leaning
    2.27
    ngth
    2.09
    cipled
    2.07
    Democrats
    2.06
    blow
    2.05
     Kush
    2.04
    govtrack
    2.02
    ト
    2.00
    Activations Density 0.003%

    No Known Activations