© 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. 20075
    Prev
    Next
    INDEX
    Explanations

    references to impeachment and associated political actions

    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
    0:0.17
    1:0.07
    2:0.03
    3:0.05
    4:0.04
    5:0.02
    6:0.24
    7:0.12
    8:0.01
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     HH
    -3.06
     festival
    -2.88
    vation
    -2.81
     Nano
    -2.80
     recru
    -2.75
    achine
    -2.69
     Shelter
    -2.67
     Goth
    -2.61
     Typh
    -2.60
    catch
    -2.55
    POSITIVE LOGITS
     impeachment
    8.77
     impe
    7.37
     indict
    4.21
     Constitutional
    4.12
     Watergate
    4.00
     Mueller
    3.92
     Prosecut
    3.85
     constitutional
    3.78
     indictment
    3.77
     perjury
    3.76
    Activations Density 0.008%

    No Known Activations