© 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. 9054
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and feelings related to personal experiences

    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
    1:0.03
    2:0.04
    3:0.19
    4:0.11
    5:0.08
    6:0.05
    7:0.04
    8:0.19
    9:0.03
    10:0.05
    11:0.06
    Negative Logits
     Cologne
    -2.93
     Lionel
    -2.92
     Belarus
    -2.85
     Germany
    -2.84
    Germany
    -2.80
     Canadiens
    -2.71
     Philippe
    -2.68
     Austria
    -2.64
     Frankfurt
    -2.62
     Barclays
    -2.61
    POSITIVE LOGITS
     kh
    4.69
     dh
    4.67
     ki
    4.44
     ka
    4.30
     sar
    3.78
    dh
    3.77
     mand
    3.76
     curry
    3.67
     mah
    3.66
     Gujar
    3.62
    Activations Density 0.036%

    No Known Activations