© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10590
    Prev
    Next
    INDEX
    Explanations

    themes related to societal and political issues, particularly around justice and individual rights

    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
    0:0.01
    1:0.01
    2:0.39
    3:0.17
    4:0.10
    5:0.08
    6:0.01
    7:0.04
    8:0.03
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
    �士
    -3.86
    \">
    -3.62
    ForgeModLoader
    -3.35
    CLASSIFIED
    -3.35
    00200000
    -3.28
    ��
    -3.21
    >"
    -3.17
    ドラ
    -3.05
    -+-+
    -3.03
    centered
    -3.00
    POSITIVE LOGITS
     Nicola
    4.44
     Read
    4.40
     Geoff
    4.13
     Nick
    3.89
     Mark
    3.87
     Matthew
    3.86
     Ian
    3.80
     Tim
    3.79
     Jamie
    3.78
     Greg
    3.74
    Activations Density 0.223%

    No Known Activations