© 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. 14118
    Prev
    Next
    INDEX
    Explanations

    phrases indicating severity or significant importance

    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
    0:0.04
    1:0.22
    2:0.07
    3:0.06
    4:0.03
    5:0.04
    6:0.14
    7:0.04
    8:0.04
    9:0.22
    10:0.03
    11:0.02
    Negative Logits
    �
    -3.54
     Atkinson
    -3.19
    oult
    -3.13
     reluct
    -3.04
     Ol
    -2.95
     ank
    -2.93
    Ol
    -2.87
     �
    -2.81
     Orwell
    -2.76
    �
    -2.72
    POSITIVE LOGITS
    serious
    5.09
     serious
    4.85
     seriously
    4.69
     Serious
    4.13
     seriousness
    3.92
    grave
    3.50
     grave
    3.50
     Stam
    3.48
     Dire
    3.28
     Danger
    3.23
    Activations Density 0.001%

    No Known Activations