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. 7-ATT-KK
    6. 9551
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions regarding taxes and economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.13
    2:0.03
    3:0.05
    4:0.03
    5:0.15
    6:0.30
    7:0.04
    8:0.05
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     adventurers
    -2.72
     beginners
    -2.51
     explorers
    -2.45
     [&
    -2.30
     chall
    -2.22
     inval
    -2.19
     mages
    -2.17
     glim
    -2.09
     cooperative
    -2.08
     Slayer
    -2.08
    POSITIVE LOGITS
    Trump
    3.49
     RNC
    3.29
    Romney
    3.24
    Republicans
    3.22
     Corker
    3.21
    Republican
    3.19
     Politico
    3.19
     GOP
    3.18
     MSNBC
    3.10
    Obama
    3.07
    Activations Density 1.398%

    No Known Activations