© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1728
    Prev
    Next
    INDEX
    Explanations

    phrases that express principles of equality and justice

    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
    1:0.02
    2:0.17
    3:0.08
    4:0.05
    5:0.10
    6:0.07
    7:0.06
    8:0.17
    9:0.04
    10:0.03
    11:0.05
    Negative Logits
     Glock
    -3.34
     Irma
    -3.19
     Rubio
    -3.16
    Miami
    -3.16
     Hurricane
    -3.10
     Miami
    -3.03
     Eliot
    -3.00
    lando
    -2.99
     Wolfgang
    -2.90
    ricane
    -2.89
    POSITIVE LOGITS
     caste
    7.43
     Dal
    4.44
     Hindu
    4.07
     Hindus
    3.93
     reservation
    3.86
     Singh
    3.77
     occupations
    3.64
     Hindi
    3.64
     Indians
    3.61
     tribe
    3.55
    Activations Density 0.001%

    No Known Activations