© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    references to Gawker and its impact on media and society

    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
    0:0.17
    1:0.06
    2:0.08
    3:0.07
    4:0.06
    5:0.02
    6:0.15
    7:0.07
    8:0.03
    9:0.04
    10:0.14
    11:0.05
    Negative Logits
     conductor
    -3.48
     indo
    -3.35
     RD
    -3.28
     pollen
    -3.00
     planners
    -2.98
     pedal
    -2.97
     MN
    -2.96
     domest
    -2.88
     Instrument
    -2.88
     Fra
    -2.84
    POSITIVE LOGITS
     Gawker
    9.78
     Hogan
    6.10
     Hulk
    5.00
     Gamergate
    3.94
     Hannity
    3.86
     Dawson
    3.79
     TMZ
    3.79
     Gotham
    3.77
     BuzzFeed
    3.72
     GamerGate
    3.64
    Activations Density 0.010%

    No Known Activations