© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18865
    Prev
    Next
    INDEX
    Explanations

    cooking instructions or processes

    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
    0:0.19
    1:0.03
    2:0.04
    3:0.11
    4:0.07
    5:0.07
    6:0.04
    7:0.08
    8:0.19
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     Sharks
    -2.78
     Frem
    -2.70
     rooftop
    -2.69
     Texans
    -2.68
     Sacramento
    -2.67
     Mak
    -2.63
     Morales
    -2.63
     architect
    -2.62
     Korra
    -2.62
     Architecture
    -2.61
    POSITIVE LOGITS
     mixer
    2.94
     flour
    2.87
    riched
    2.84
     mixture
    2.81
    ixture
    2.81
    ocolate
    2.73
     yeast
    2.53
    mouth
    2.52
    udding
    2.52
     dough
    2.50
    Activations Density 0.018%

    No Known Activations