© 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 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. 13351
    Prev
    Next
    INDEX
    Explanations

    references to ancient historical findings related to the Egyptian pyramids and their builders

    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
    1:0.01
    2:0.10
    3:0.14
    4:0.03
    5:0.11
    6:0.03
    7:0.04
    8:0.35
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     Clancy
    -4.09
     VMware
    -3.58
     Buckley
    -3.44
     Hockey
    -3.43
     Blackhawks
    -3.16
     Gallagher
    -3.14
     Kennedy
    -3.12
     Snowden
    -3.10
     McGu
    -3.06
     Burlington
    -3.04
    POSITIVE LOGITS
     Pharaoh
    5.48
     Herod
    5.41
     Egyptians
    5.26
     Osiris
    5.19
    araoh
    4.90
     Assy
    4.75
     Egyptian
    4.72
    Egypt
    4.65
     Babylon
    4.54
     Egypt
    4.33
    Activations Density 0.241%

    No Known Activations