© 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. 20296
    Prev
    Next
    INDEX
    Explanations

    descriptions of complex and ambiguous characters or scenarios

    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
    0:0.16
    1:0.06
    2:0.09
    3:0.05
    4:0.04
    5:0.03
    6:0.15
    7:0.09
    8:0.02
    9:0.06
    10:0.15
    11:0.04
    Negative Logits
     Navajo
    -3.53
     Mex
    -3.47
     Cort
    -3.08
     Chip
    -2.97
    Taylor
    -2.94
     Whitman
    -2.88
     resil
    -2.86
    illac
    -2.84
     TC
    -2.83
     HC
    -2.83
    POSITIVE LOGITS
     Boris
    8.86
    oris
    4.25
     Bulgaria
    4.18
     Dmitry
    3.99
     Euros
    3.93
     Vladimir
    3.71
     UKIP
    3.67
     Bulgarian
    3.63
     Denis
    3.62
     Farage
    3.61
    Activations Density 0.001%

    No Known Activations