© 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. 4801
    Prev
    Next
    INDEX
    Explanations

    references to laborers and their historical context in relation to the construction of the pyramids

    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
    0:0.15
    1:0.02
    2:0.17
    3:0.06
    4:0.05
    5:0.05
    6:0.10
    7:0.04
    8:0.16
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
     Grimes
    -3.80
     Reilly
    -3.77
     Hayes
    -3.54
     Gallagher
    -3.49
     Greenwald
    -3.25
    dayName
    -3.25
     Carey
    -3.23
    こ
    -3.18
    azines
    -3.10
    netflix
    -3.04
    POSITIVE LOGITS
     Pyramid
    9.15
     pyramid
    8.84
    ramids
    6.75
     Pharaoh
    6.41
    ramid
    6.27
     py
    5.67
    araoh
    5.29
     Sph
    5.23
     Egyptian
    4.68
    Egypt
    4.55
    Activations Density 0.003%

    No Known Activations