© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 5535
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to political power dynamics and legislation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.08
    3:0.04
    4:0.07
    5:0.06
    6:0.16
    7:0.05
    8:0.07
    9:0.27
    10:0.02
    11:0.04
    Negative Logits
     Robbins
    -4.45
    Rob
    -3.60
     Blake
    -3.46
    boot
    -3.34
    boy
    -3.32
     Boot
    -3.31
    Blake
    -3.23
    Boy
    -3.21
     Brighton
    -3.08
    Boot
    -3.06
    POSITIVE LOGITS
     Congress
    6.55
    Congress
    6.32
     Congressional
    5.90
     congressional
    5.77
     congress
    5.63
     lawmakers
    5.60
     Legisl
    5.56
     legislators
    5.48
     Parliament
    5.48
     Capitol
    5.18
    Activations Density 0.029%

    No Known Activations