© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20474
    Prev
    Next
    INDEX
    Explanations

    statements or phrases indicating ongoing conversations or collaborations

    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
    0:0.10
    1:0.02
    2:0.08
    3:0.03
    4:0.06
    5:0.04
    6:0.23
    7:0.05
    8:0.06
    9:0.23
    10:0.02
    11:0.04
    Negative Logits
     Cheryl
    -3.81
     Chin
    -3.69
     Neck
    -3.61
    emouth
    -3.60
    ukong
    -3.57
    ierrez
    -3.50
     Chilean
    -3.37
    atown
    -3.36
    cks
    -3.35
     CAT
    -3.30
    POSITIVE LOGITS
     Fro
    11.03
     fro
    5.88
    Fra
    5.37
     Fra
    5.34
     hob
    4.47
     Gand
    4.46
     Gam
    4.36
     Roche
    4.25
     Gro
    4.13
    Gro
    4.10
    Activations Density 0.001%

    No Known Activations