© 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. 15034
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or conditions in statements

    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
    0:0.07
    1:0.03
    2:0.10
    3:0.04
    4:0.04
    5:0.03
    6:0.21
    7:0.04
    8:0.08
    9:0.23
    10:0.03
    11:0.03
    Negative Logits
     Punk
    -4.37
    Band
    -3.77
     Buchanan
    -3.76
     Kaz
    -3.72
    GD
    -3.70
     spons
    -3.67
     Sv
    -3.61
     antis
    -3.52
     PVC
    -3.47
     punk
    -3.44
    POSITIVE LOGITS
     Emer
    9.27
    Emer
    8.33
     Arri
    5.71
     emer
    5.54
    emer
    4.76
     Emerald
    4.39
     Prophe
    4.28
    ember
    4.25
     Revel
    3.82
     Aure
    3.79
    Activations Density 0.000%

    No Known Activations