© 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. 9-ATT-KK
    11. 9180
    Prev
    Next
    INDEX
    Explanations

    polling data related to political opinions and approval ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.03
    2:0.09
    3:0.31
    4:0.04
    5:0.16
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.07
    11:0.03
    Negative Logits
    artifacts
    -1.79
     millennia
    -1.74
     caches
    -1.73
     arte
    -1.72
    products
    -1.65
     miraculous
    -1.65
     renovations
    -1.64
     nano
    -1.64
     counterfe
    -1.63
     portable
    -1.61
    POSITIVE LOGITS
     respondents
    3.21
     polled
    2.83
     Voters
    2.71
     undecided
    2.52
     Democrats
    2.49
     Liberals
    2.47
     voters
    2.42
    Republicans
    2.39
     disapprove
    2.35
     Republicans
    2.30
    Activations Density 0.553%

    No Known Activations