© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21330
    Prev
    Next
    INDEX
    Explanations

    references to political roles and titles, particularly those related to chairpersons and secretaries

    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
    0:0.14
    1:0.05
    2:0.05
    3:0.05
    4:0.15
    5:0.03
    6:0.19
    7:0.10
    8:0.02
    9:0.04
    10:0.05
    11:0.07
    Negative Logits
     volunt
    -3.07
    pring
    -2.89
    Clinton
    -2.89
    Hillary
    -2.85
     Hillary
    -2.81
     Butterfly
    -2.79
     prosecutors
    -2.75
    clinton
    -2.74
     DOC
    -2.73
    orneys
    -2.73
    POSITIVE LOGITS
     Hanna
    2.98
     Lars
    2.64
     Ways
    2.62
     Subcommittee
    2.61
    pipe
    2.52
     amd
    2.50
     pipeline
    2.48
     CRA
    2.48
     Vikings
    2.46
     crafts
    2.43
    Activations Density 0.002%

    No Known Activations