© 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. 7621
    Prev
    Next
    INDEX
    Explanations

    phrases related to allegations and legal actions involving serious misconduct

    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
    0:0.24
    1:0.06
    2:0.05
    3:0.05
    4:0.06
    5:0.04
    6:0.09
    7:0.12
    8:0.02
    9:0.05
    10:0.12
    11:0.05
    Negative Logits
    brush
    -3.31
     camouflage
    -3.09
     Ubisoft
    -3.06
     patch
    -3.02
     Blades
    -3.01
     Paulo
    -2.96
    patch
    -2.88
     cape
    -2.85
     pokemon
    -2.85
     brush
    -2.82
    POSITIVE LOGITS
     Kramer
    8.31
     Elaine
    5.21
    ramer
    5.21
    Jerry
    4.67
    infeld
    4.65
     Jerry
    4.20
     Kau
    3.52
     Newman
    3.40
    �
    3.28
     Kaufman
    3.24
    Activations Density 0.004%

    No Known Activations