© 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. 20729
    Prev
    Next
    INDEX
    Explanations

    references to regulations and policies in relation to specific sectors or practices

    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
    0:0.06
    1:0.07
    2:0.08
    3:0.06
    4:0.06
    5:0.02
    6:0.04
    7:0.31
    8:0.03
    9:0.05
    10:0.09
    11:0.08
    Negative Logits
     Refugee
    -3.03
     Chess
    -2.65
     Refugees
    -2.62
     Witches
    -2.46
     dstg
    -2.44
     Abortion
    -2.43
     Rape
    -2.39
     Rabbit
    -2.38
     Narc
    -2.36
     Genocide
    -2.36
    POSITIVE LOGITS
     allowable
    1.97
    unta
    1.95
    phis
    1.88
     situ
    1.84
     colle
    1.78
    ulent
    1.74
     federally
    1.74
    vention
    1.73
    erous
    1.72
    orously
    1.70
    Activations Density 0.787%

    No Known Activations