© 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. 22060
    Prev
    Next
    INDEX
    Explanations

    discussions around representation and inclusion, particularly in the context of marginalized groups

    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
    0:0.04
    1:0.29
    2:0.05
    3:0.05
    4:0.05
    5:0.05
    6:0.10
    7:0.06
    8:0.04
    9:0.14
    10:0.03
    11:0.05
    Negative Logits
     TAMADRA
    -2.90
    catentry
    -2.79
    EMA
    -2.47
     �
    -2.46
     Tower
    -2.45
     TRUMP
    -2.38
     Chung
    -2.32
     WATCHED
    -2.31
    eling
    -2.31
     Tik
    -2.28
    POSITIVE LOGITS
    non
    5.19
     NON
    4.51
     non
    4.39
    Non
    4.25
     Non
    4.24
     nonex
    3.50
     nons
    3.39
    outube
    2.93
    NO
    2.70
    alk
    2.69
    Activations Density 0.005%

    No Known Activations