© 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. 7530
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols related to dialogue and quotations

    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
    1:0.03
    2:0.04
    3:0.04
    4:0.03
    5:0.03
    6:0.16
    7:0.04
    8:0.05
    9:0.43
    10:0.03
    11:0.02
    Negative Logits
     Bean
    -4.87
     bean
    -4.27
     Stamp
    -3.74
     progressives
    -3.65
     Monk
    -3.64
     Booth
    -3.64
     Pod
    -3.62
    kamp
    -3.58
     Brooke
    -3.48
     monk
    -3.41
    POSITIVE LOGITS
    ir
    7.44
    IR
    7.22
     IR
    7.08
    Ir
    6.60
    iris
    6.11
     Ir
    6.07
     Kir
    5.99
     ir
    5.79
     Vir
    5.39
    irs
    5.33
    Activations Density 0.021%

    No Known Activations