© 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. 544
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reactions in dialogue

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.12
    4:0.07
    5:0.07
    6:0.02
    7:0.07
    8:0.38
    9:0.02
    10:0.03
    11:0.05
    Negative Logits
     Philly
    -2.67
     Philadelphia
    -2.56
     Byrne
    -2.34
     CBS
    -2.32
     Semin
    -2.30
     Buckley
    -2.28
     Dodd
    -2.28
     federally
    -2.28
     McKenna
    -2.27
     Delaware
    -2.25
    POSITIVE LOGITS
    『
    5.59
    【
    4.96
    ──
    4.54
     「
    4.45
    「
    4.08
    】
    3.96
    �
    3.86
    』
    3.75
     Takeru
    3.65
    sama
    3.57
    Activations Density 0.292%

    No Known Activations