© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21499
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" indicating contrasting or concurrent situations

    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
    0:0.09
    1:0.02
    2:0.09
    3:0.05
    4:0.04
    5:0.03
    6:0.25
    7:0.05
    8:0.10
    9:0.17
    10:0.02
    11:0.05
    Negative Logits
     cryptoc
    -4.02
     Property
    -3.87
    phalt
    -3.76
     Speedway
    -3.72
    Property
    -3.57
    UX
    -3.56
    vette
    -3.50
     ‎
    -3.40
    intosh
    -3.38
     asphalt
    -3.30
    POSITIVE LOGITS
     Hag
    11.54
     Hed
    4.69
     Nag
    4.60
     Hog
    4.58
     Dag
    4.57
     Hers
    4.45
     Eag
    4.26
     Hod
    4.23
     Hir
    4.18
     Hansen
    4.13
    Activations Density 0.002%

    No Known Activations