© 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. 16797
    Prev
    Next
    INDEX
    Explanations

    references to tax policy and wealth distribution

    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
    0:0.10
    1:0.04
    2:0.09
    3:0.13
    4:0.07
    5:0.18
    6:0.04
    7:0.08
    8:0.06
    9:0.04
    10:0.08
    11:0.04
    Negative Logits
     Sapp
    -2.27
     prostitutes
    -2.22
     billboards
    -2.11
    racial
    -2.10
     discriminatory
    -2.06
     flirt
    -2.03
     Sob
    -2.00
     posters
    -1.98
     alcoholism
    -1.98
     Cros
    -1.96
    POSITIVE LOGITS
     possessions
    1.90
    ��
    1.85
    held
    1.83
     Warlock
    1.81
     assets
    1.79
    minus
    1.76
    arent
    1.70
     stead
    1.70
     essentials
    1.69
    azor
    1.69
    Activations Density 0.013%

    No Known Activations