© 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. 13717
    Prev
    Next
    INDEX
    Explanations

    references to geological time scales and the age of the Earth

    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
    0:0.07
    1:0.01
    2:0.37
    3:0.10
    4:0.03
    5:0.10
    6:0.03
    7:0.05
    8:0.10
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     Customers
    -2.53
     Blasio
    -2.53
     firewall
    -2.52
     FISA
    -2.51
    oshenko
    -2.50
     uninsured
    -2.49
     NYPD
    -2.46
     Customer
    -2.46
     CTR
    -2.45
     handcuffs
    -2.43
    POSITIVE LOGITS
     prehistoric
    5.08
     fossils
    5.00
     Archae
    4.87
     archaeological
    4.76
     extinct
    4.73
     archae
    4.67
     archaeologists
    4.58
     Neander
    4.43
     geological
    4.42
     Paleo
    4.18
    Activations Density 0.545%

    No Known Activations