© 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. 10-ATT-KK
    11. 21089
    Prev
    Next
    INDEX
    Explanations

    references to identity and societal challenges faced by marginalized groups

    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
    1:0.03
    2:0.05
    3:0.06
    4:0.06
    5:0.11
    6:0.02
    7:0.04
    8:0.03
    9:0.42
    10:0.02
    11:0.08
    Negative Logits
    iliated
    -2.59
    xual
    -2.53
     motivated
    -2.15
    gyn
    -2.14
    thumbnails
    -2.07
    ceived
    -2.07
     her
    -2.05
    identified
    -2.01
     their
    -1.98
    nered
    -1.98
    POSITIVE LOGITS
     裏�
    1.98
    obiles
    1.95
    �
    1.93
    folios
    1.93
    boats
    1.92
     slipping
    1.91
    版
    1.88
    oros
    1.80
     Agric
    1.78
    facts
    1.78
    Activations Density 0.028%

    No Known Activations