© 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. 9-ATT-KK
    11. 24191
    Prev
    Next
    INDEX
    Explanations

    expressions of political opinions and actions

    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
    0:0.05
    1:0.03
    2:0.05
    3:0.06
    4:0.06
    5:0.07
    6:0.06
    7:0.07
    8:0.09
    9:0.07
    10:0.04
    11:0.30
    Negative Logits
    ``
    -4.46
    )--
    -4.41
     ``
    -4.28
     �
    -3.91
    �
    -3.85
    --
    -3.76
    '';
    -3.65
    ��
    -3.63
    .--
    -3.59
    .......
    -3.24
    POSITIVE LOGITS
     Trump
    6.32
    Trump
    4.99
     Spicer
    4.31
     Bannon
    4.30
     Tillerson
    4.02
     Rosenstein
    4.00
     Mueller
    3.97
     Pence
    3.96
     Kushner
    3.93
     Obama
    3.86
    Activations Density 0.162%

    No Known Activations