© 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. 9-ATT-KK
    11. 22177
    Prev
    Next
    INDEX
    Explanations

    discussions about political authority and conscience

    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
    0:0.06
    1:0.04
    2:0.04
    3:0.03
    4:0.05
    5:0.04
    6:0.24
    7:0.04
    8:0.07
    9:0.27
    10:0.01
    11:0.04
    Negative Logits
    erto
    -4.14
    rongh
    -4.01
     prost
    -3.59
     gobl
    -3.55
    erey
    -3.54
    edom
    -3.41
     Strongh
    -3.31
    fet
    -3.29
     Bethlehem
    -3.25
    lambda
    -3.25
    POSITIVE LOGITS
     Collins
    11.57
    Collins
    11.01
     Crowley
    4.41
     Ald
    4.20
     Cox
    4.17
    Cole
    4.17
     Higgins
    4.08
    coll
    4.08
     Conn
    4.08
     Chan
    3.96
    Activations Density 0.007%

    No Known Activations