© 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. 10-ATT-KK
    11. 10433
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to character relationships and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.28
    1:0.07
    2:0.09
    3:0.07
    4:0.05
    5:0.02
    6:0.07
    7:0.07
    8:0.02
    9:0.05
    10:0.12
    11:0.05
    Negative Logits
    etsk
    -3.96
     Macintosh
    -3.62
     Sparkle
    -3.59
    PET
    -3.56
     Lauder
    -3.51
     Wink
    -3.44
    ��
    -3.38
     puff
    -3.35
    cigarette
    -3.31
    MJ
    -3.27
    POSITIVE LOGITS
     Hannibal
    10.16
     cannibal
    5.08
    ibal
    5.07
     Lect
    4.84
     Carth
    4.78
    ylum
    4.09
     Hunger
    3.96
     HBO
    3.96
     Fuller
    3.88
     Hann
    3.85
    Activations Density 0.005%

    No Known Activations