© 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. 10-ATT-KK
    11. 7659
    Prev
    Next
    INDEX
    Explanations

    references to historical events and specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.21
    1:0.07
    2:0.06
    3:0.04
    4:0.07
    5:0.04
    6:0.07
    7:0.10
    8:0.05
    9:0.06
    10:0.11
    11:0.08
    Negative Logits
    MRI
    -3.62
     Fang
    -3.29
     MRI
    -3.21
     Bengals
    -3.09
     Narc
    -3.06
    �
    -2.98
     Weiss
    -2.97
     Sym
    -2.97
     fentanyl
    -2.96
    �
    -2.94
    POSITIVE LOGITS
     dunk
    7.76
     Dunk
    6.32
     dun
    5.26
     duck
    3.93
     ducks
    3.82
     Slam
    3.52
     pudding
    3.51
     Kidd
    3.48
     basketball
    3.43
     drib
    3.32
    Activations Density 0.001%

    No Known Activations