© 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. 9635
    Prev
    Next
    INDEX
    Explanations

    references to emotional states and relationship dynamics

    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
    0:0.04
    1:0.16
    2:0.05
    3:0.25
    4:0.04
    5:0.03
    6:0.06
    7:0.15
    8:0.02
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     神
    -2.08
     faire
    -2.06
    shaw
    -2.02
    North
    -2.00
    creation
    -1.98
     Fault
    -1.95
    hovah
    -1.92
     Forth
    -1.92
    chwitz
    -1.91
     Harvest
    -1.90
    POSITIVE LOGITS
     stay
    4.46
     Stay
    3.90
     stayed
    3.88
     stays
    3.62
    stay
    3.62
     staying
    3.58
    Stay
    3.32
     remain
    2.76
     remained
    2.49
     POLITICO
    2.16
    Activations Density 0.042%

    No Known Activations