© 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. 22743
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ass" and its variants in various contexts

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.06
    4:0.04
    5:0.04
    6:0.10
    7:0.02
    8:0.03
    9:0.52
    10:0.02
    11:0.01
    Negative Logits
     Boll
    -3.38
    ��
    -3.21
    incinnati
    -3.03
     Dion
    -2.96
     Duke
    -2.94
     Zhao
    -2.92
     marqu
    -2.87
    ogh
    -2.79
     Beam
    -2.77
    oglu
    -2.76
    POSITIVE LOGITS
    SS
    6.02
     SS
    5.57
     SAS
    5.32
    ss
    5.12
    S
    5.11
     ss
    5.01
     S
    4.64
    sv
    4.61
     Saunders
    4.59
    sa
    4.52
    Activations Density 0.500%

    No Known Activations