© 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. 482
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to loss and tribute

    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
    0:0.06
    1:0.04
    2:0.07
    3:0.04
    4:0.06
    5:0.04
    6:0.22
    7:0.06
    8:0.10
    9:0.19
    10:0.03
    11:0.04
    Negative Logits
    heit
    -3.61
     Sok
    -3.57
    antz
    -3.51
     vec
    -3.46
    cho
    -3.45
     neuron
    -3.30
     Kling
    -3.26
     Hispanics
    -3.24
     Kov
    -3.22
    ć
    -3.22
    POSITIVE LOGITS
    Royal
    8.83
     Royal
    8.71
     royal
    7.07
     roy
    5.63
    roy
    5.50
    Prin
    4.95
     monarchy
    4.94
    Queen
    4.51
     Princess
    4.45
     Queen
    4.32
    Activations Density 0.002%

    No Known Activations