© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14980
    Prev
    Next
    INDEX
    Explanations

    references to political spending and campaign finance activities

    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
    0:0.07
    1:0.04
    2:0.05
    3:0.08
    4:0.13
    5:0.03
    6:0.19
    7:0.11
    8:0.02
    9:0.06
    10:0.05
    11:0.13
    Negative Logits
     psychiat
    -3.00
     solved
    -2.75
    ��
    -2.70
     civilisation
    -2.68
     Instructor
    -2.63
     apologise
    -2.61
     realise
    -2.58
    reci
    -2.54
    iculture
    -2.52
    bane
    -2.52
    POSITIVE LOGITS
     PACs
    6.63
     PAC
    5.82
     FEC
    5.65
     fundra
    5.61
     fundraising
    5.56
     donors
    5.32
    PAC
    5.02
     nonprofits
    4.94
     campaign
    4.90
    Campaign
    4.86
    Activations Density 0.405%

    No Known Activations