© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    phrases indicating political dynamics and electoral outcomes

    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
    0:0.15
    1:0.03
    2:0.19
    3:0.12
    4:0.05
    5:0.11
    6:0.05
    7:0.07
    8:0.06
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     greeting
    -2.23
     Ripple
    -2.10
     crochet
    -2.07
     Init
    -2.05
    respond
    -2.04
     testim
    -2.04
     manic
    -1.94
     sincerity
    -1.87
    Response
    -1.86
     rave
    -1.86
    POSITIVE LOGITS
     seats
    3.66
     incumb
    3.46
     constituencies
    3.06
     elector
    3.05
     seat
    3.04
     vacancies
    2.95
    Democrats
    2.88
     Seat
    2.83
     incumbent
    2.80
     districts
    2.76
    Activations Density 0.122%

    No Known Activations