© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their actions or characteristics

    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
    1:0.02
    2:0.05
    3:0.22
    4:0.04
    5:0.05
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.33
    11:0.03
    Negative Logits
    until
    -2.28
     until
    -2.13
    NetMessage
    -2.04
    reating
    -1.97
    �醒
    -1.94
    ibrary
    -1.93
     Activate
    -1.93
    Suddenly
    -1.93
    iru
    -1.91
     Millenn
    -1.91
    POSITIVE LOGITS
     differed
    3.15
     disagreed
    3.06
     declined
    3.01
     cautioned
    2.97
     nonetheless
    2.96
     occasional
    2.95
     nevertheless
    2.88
     caveats
    2.86
     occasionally
    2.80
     doubtful
    2.77
    Activations Density 0.125%

    No Known Activations