© 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. 2074
    Prev
    Next
    INDEX
    Explanations

    discourse surrounding prominent figures and their statements or actions in the context of political events

    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
    1:0.03
    2:0.05
    3:0.04
    4:0.06
    5:0.04
    6:0.18
    7:0.05
    8:0.07
    9:0.31
    10:0.02
    11:0.04
    Negative Logits
     haz
    -3.71
     Overwatch
    -3.51
     Hastings
    -3.40
    Tes
    -3.29
     Razer
    -3.28
    yna
    -3.23
    ulner
    -3.17
     ASIC
    -3.17
     hashes
    -3.16
    olson
    -3.15
    POSITIVE LOGITS
     Paul
    8.44
    Paul
    8.34
     Paula
    4.98
     Ron
    4.97
     Philipp
    4.71
     Paulo
    4.39
     Rand
    4.32
    Ron
    4.28
    Philipp
    4.06
     Carol
    4.04
    Activations Density 0.031%

    No Known Activations