© 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. 9-ATT-KK
    11. 14643
    Prev
    Next
    INDEX
    Explanations

    emphasized emotional 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
    0:0.13
    1:0.03
    2:0.05
    3:0.08
    4:0.12
    5:0.07
    6:0.08
    7:0.08
    8:0.18
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
     Wilmington
    -3.08
     incorpor
    -2.95
     Chavez
    -2.74
     Haitian
    -2.70
     charter
    -2.69
     Newark
    -2.68
     Hughes
    -2.64
     Delaware
    -2.60
     Thur
    -2.50
     Americ
    -2.49
    POSITIVE LOGITS
    �
    4.64
     �
    3.89
    ‎
    3.34
    Anna
    3.23
     Elsa
    3.12
    Elsa
    2.98
    ヘ
    2.96
    �
    2.92
    人
    2.88
    ノ
    2.83
    Activations Density 0.732%

    No Known Activations