© 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. 15608
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice and discrimination issues

    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
    0:0.11
    1:0.11
    2:0.07
    3:0.05
    4:0.06
    5:0.02
    6:0.08
    7:0.18
    8:0.03
    9:0.03
    10:0.13
    11:0.07
    Negative Logits
    ッド
    -2.92
    horn
    -2.50
    Enlarge
    -2.44
    ohyd
    -2.39
     silicone
    -2.35
     electroly
    -2.33
     Bou
    -2.24
    oux
    -2.23
     Grimes
    -2.22
     Fay
    -2.21
    POSITIVE LOGITS
     antis
    5.16
     Zionism
    2.81
     Holocaust
    2.54
    Israel
    2.51
     Ant
    2.44
     Israel
    2.40
     Naz
    2.36
     Amos
    2.35
     sociop
    2.34
     Juda
    2.34
    Activations Density 0.001%

    No Known Activations