© 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. 18989
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and interactions among characters

    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
    0:0.07
    1:0.05
    2:0.11
    3:0.13
    4:0.07
    5:0.10
    6:0.02
    7:0.12
    8:0.07
    9:0.02
    10:0.10
    11:0.09
    Negative Logits
     MILL
    -1.88
     IRA
    -1.85
     Pigs
    -1.83
    )</
    -1.82
    ™:
    -1.78
    Sov
    -1.77
     TDs
    -1.74
    vernment
    -1.72
     lakh
    -1.72
    ombo
    -1.72
    POSITIVE LOGITS
     herself
    3.25
     her
    3.17
     she
    2.88
     hers
    2.86
     Jaune
    2.53
     Weiss
    2.46
     nodded
    2.44
    She
    2.34
     nervously
    2.33
     Static
    2.32
    Activations Density 0.116%

    No Known Activations