© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    conversations and interactions among people

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.03
    4:0.06
    5:0.04
    6:0.13
    7:0.06
    8:0.08
    9:0.35
    10:0.02
    11:0.04
    Negative Logits
    hess
    -3.76
    mers
    -3.43
     NVIDIA
    -3.37
     CET
    -3.34
     redist
    -3.29
    LG
    -3.19
     Nvidia
    -3.17
    ür
    -3.14
     Greens
    -3.13
     glim
    -3.05
    POSITIVE LOGITS
     Joe
    8.44
    Joe
    8.00
     Joey
    5.87
     jo
    4.99
     Biden
    4.81
     Joseph
    4.55
    Joseph
    4.22
    oji
    3.97
     Robo
    3.96
     Angelo
    3.95
    Activations Density 0.012%

    No Known Activations