© 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. 13316
    Prev
    Next
    INDEX
    Explanations

    phrases related to demographics, particularly focusing on racial and ethnic group classifications

    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
    0:0.03
    1:0.04
    2:0.03
    3:0.07
    4:0.22
    5:0.02
    6:0.03
    7:0.26
    8:0.02
    9:0.03
    10:0.03
    11:0.15
    Negative Logits
    ]).
    -2.51
     negro
    -2.39
    ...]
    -2.22
    *)
    -2.19
    …]
    -2.19
    ...)
    -2.19
    …)
    -2.14
     idiot
    -2.12
    ….
    -2.10
    …
    -2.03
    POSITIVE LOGITS
    Keys
    2.19
     DeVos
    2.01
     Roe
    1.99
     Kissinger
    1.97
     Podesta
    1.96
     Booker
    1.96
     preached
    1.95
     Key
    1.94
     Chambers
    1.91
     Pell
    1.90
    Activations Density 0.014%

    No Known Activations