© 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. 16173
    Prev
    Next
    INDEX
    Explanations

    references to political actions and issues related to law and governance

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.07
    4:0.15
    5:0.40
    6:0.03
    7:0.05
    8:0.03
    9:0.07
    10:0.02
    11:0.04
    Negative Logits
    VERTISEMENT
    -3.63
    Enlarge
    -3.20
    toggle
    -2.99
     dunno
    -2.88
    ッド
    -2.75
     Weird
    -2.63
    Poké
    -2.61
     Stuff
    -2.61
    izzle
    -2.55
    +.
    -2.54
    POSITIVE LOGITS
     cannot
    5.54
     must
    4.90
     deserves
    4.59
     deserve
    4.43
     urgently
    4.33
     should
    4.27
     ought
    4.26
     needs
    4.24
     will
    4.14
     condemns
    4.08
    Activations Density 1.112%

    No Known Activations