© 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. 5-ATT-KK
    11. 27255
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and their roles within the House of Representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.03
    6:0.22
    7:0.35
    8:0.03
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    nown
    -1.69
     stash
    -1.54
    dates
    -1.53
    idious
    -1.51
    fman
    -1.51
    erion
    -1.46
    opian
    -1.45
    anchez
    -1.45
    umbnails
    -1.42
     inventions
    -1.41
    POSITIVE LOGITS
     chorus
    1.66
     Lansing
    1.63
    aca
    1.57
    Song
    1.43
    の�
    1.38
    horn
    1.37
    division
    1.37
     Shade
    1.34
    current
    1.32
     Congress
    1.32
    Activations Density 0.002%

    No Known Activations