© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    occurrences of strong opinions or affirmations about an idea or product

    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
    0:0.08
    1:0.11
    2:0.08
    3:0.04
    4:0.03
    5:0.04
    6:0.17
    7:0.04
    8:0.04
    9:0.21
    10:0.05
    11:0.04
    Negative Logits
     Farrell
    -3.69
     screens
    -3.40
    ince
    -3.33
     Chimera
    -3.16
     Walsh
    -3.08
     Catalyst
    -3.02
     McCabe
    -2.91
     Cinema
    -2.91
     Hitchcock
    -2.90
     Cot
    -2.83
    POSITIVE LOGITS
     belong
    5.27
     belonged
    4.77
     belongs
    4.71
     Lod
    4.08
     belonging
    3.93
    ods
    3.66
     Yug
    3.46
     LEGO
    3.28
     owe
    3.19
    Leg
    3.15
    Activations Density 0.001%

    No Known Activations