© 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. 13232
    Prev
    Next
    INDEX
    Explanations

    discussion points concerning privilege and social inequality

    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
    0:0.07
    1:0.16
    2:0.05
    3:0.06
    4:0.11
    5:0.02
    6:0.12
    7:0.11
    8:0.02
    9:0.04
    10:0.07
    11:0.12
    Negative Logits
    adoes
    -2.43
     Volunteers
    -2.43
    clean
    -2.38
    �
    -2.36
     Sparks
    -2.32
     Moody
    -2.30
     Rocks
    -2.22
     Cumber
    -2.21
     Telegram
    -2.18
    Alert
    -2.17
    POSITIVE LOGITS
     privilege
    6.22
    ilege
    5.78
     privileges
    5.23
     privileged
    5.09
    Priv
    4.78
     Priv
    4.71
    priv
    4.19
     privile
    3.67
     chau
    3.50
     entitlement
    3.48
    Activations Density 0.006%

    No Known Activations