© 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. 12629
    Prev
    Next
    INDEX
    Explanations

    elements of a dialogue or conversation, along with punctuation markers

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.04
    4:0.07
    5:0.02
    6:0.29
    7:0.04
    8:0.03
    9:0.29
    10:0.02
    11:0.03
    Negative Logits
     Leone
    -3.81
     EMP
    -3.59
    ince
    -3.48
    oleon
    -3.47
    walker
    -3.00
    Sav
    -2.99
     turtles
    -2.96
     tiger
    -2.96
     zombies
    -2.95
     shovel
    -2.93
    POSITIVE LOGITS
     Bib
    5.22
     B
    5.15
    B
    4.65
     BDS
    4.57
     Bud
    4.55
     BA
    4.54
     IB
    4.42
    BA
    4.40
     Bhar
    4.26
     b
    4.20
    Activations Density 0.059%

    No Known Activations