© 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. 408
    Prev
    Next
    INDEX
    Explanations

    expressions related to uncertainty or inconclusiveness

    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
    0:0.02
    1:0.03
    2:0.02
    3:0.05
    4:0.02
    5:0.05
    6:0.34
    7:0.03
    8:0.02
    9:0.03
    10:0.10
    11:0.23
    Negative Logits
    ––
    -4.31
    ●
    -4.30
    \\
    -4.02
    ­
    -4.01
    \\\\
    -3.81
    ||
    -3.65
    �
    -3.60
     ­
    -3.50
    —-
    -3.48
    �
    -3.47
    POSITIVE LOGITS
     Templ
    2.88
    ulkan
    2.88
     Anim
    2.87
     Kyoto
    2.81
    mares
    2.65
     McH
    2.61
     Yad
    2.60
     mum
    2.59
     Metatron
    2.58
     MLB
    2.58
    Activations Density 0.359%

    No Known Activations