© 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. 16298
    Prev
    Next
    INDEX
    Explanations

    phrases indicating decision-making or evaluations

    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
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.27
    7:0.04
    8:0.05
    9:0.31
    10:0.02
    11:0.03
    Negative Logits
     Squid
    -4.20
    Squ
    -4.20
     pee
    -4.06
     Slime
    -3.88
     bur
    -3.67
     Squ
    -3.66
     Reeves
    -3.66
     Khe
    -3.64
     squid
    -3.64
     ESC
    -3.59
    POSITIVE LOGITS
    Martin
    10.58
     Martin
    9.96
    mart
    5.61
    Mart
    5.44
     mart
    4.82
     Marty
    4.76
     Mart
    4.54
     Zimmerman
    4.31
     Sanford
    4.07
    Ma
    4.04
    Activations Density 0.011%

    No Known Activations