© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14531
    Prev
    Next
    INDEX
    Explanations

    positive expressions of gratitude and exceptional experiences related to gift-giving

    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
    0:0.40
    1:0.01
    2:0.13
    3:0.08
    4:0.04
    5:0.09
    6:0.01
    7:0.05
    8:0.02
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
    Management
    -2.62
    MSN
    -2.57
    kefeller
    -2.19
     Jazeera
    -2.14
     ¶
    -2.14
    Appearances
    -2.12
    natureconservancy
    -2.08
    aspers
    -2.05
    azeera
    -2.02
    Tap
    -2.02
    POSITIVE LOGITS
     gifts
    3.02
     postal
    3.00
     Gifts
    2.86
     gift
    2.77
     rematch
    2.74
     Santa
    2.73
     gif
    2.69
    Santa
    2.69
     USPS
    2.64
     quantity
    2.60
    Activations Density 0.028%

    No Known Activations