© 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. 10-ATT-KK
    11. 21216
    Prev
    Next
    INDEX
    Explanations

    references to political controversies and parliamentary procedures

    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
    0:0.01
    1:0.01
    2:0.02
    3:0.06
    4:0.13
    5:0.53
    6:0.01
    7:0.04
    8:0.02
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
     Written
    -3.03
     Flavoring
    -2.81
     attm
    -2.69
    racuse
    -2.69
    Yep
    -2.65
     Comes
    -2.52
    rawdownloadcloneembedreportprint
    -2.50
    Writ
    -2.49
    Amazing
    -2.48
    Huh
    -2.46
    POSITIVE LOGITS
     had
    5.77
     hadn
    5.74
     lacked
    5.65
     depended
    5.07
     amounted
    5.07
     risked
    5.02
     remained
    4.96
     would
    4.89
     differed
    4.64
     resembled
    4.58
    Activations Density 2.112%

    No Known Activations