© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    conversational phrases that indicate a topic shift or questioning

    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
    0:0.05
    1:0.05
    2:0.04
    3:0.07
    4:0.38
    5:0.06
    6:0.06
    7:0.06
    8:0.03
    9:0.05
    10:0.03
    11:0.06
    Negative Logits
    ancial
    -3.14
    arers
    -3.06
    avorite
    -3.01
    essage
    -2.99
    ciplinary
    -2.94
    iminary
    -2.92
    iquette
    -2.86
    ottest
    -2.84
     dashed
    -2.70
    icious
    -2.69
    POSITIVE LOGITS
     JACK
    3.60
     KING
    3.54
     KR
    3.50
     HAM
    3.49
     WA
    3.45
     KH
    3.42
     UW
    3.42
     MAR
    3.34
     MIL
    3.31
    Q
    3.27
    Activations Density 0.026%

    No Known Activations