© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant emotional responses or reasoning

    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
    0:0.10
    1:0.05
    2:0.10
    3:0.04
    4:0.03
    5:0.02
    6:0.22
    7:0.03
    8:0.03
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
    gdala
    -4.68
     Labrador
    -3.92
     Barney
    -3.74
     Lamb
    -3.69
     Huss
    -3.66
     fem
    -3.51
    berus
    -3.49
    apore
    -3.46
     filament
    -3.43
     Campbell
    -3.43
    POSITIVE LOGITS
     Win
    8.42
    Win
    8.04
    win
    7.85
     WIN
    7.62
    WIN
    7.54
     win
    6.59
     Wins
    6.45
     Winning
    5.66
     wins
    5.42
     winning
    4.61
    Activations Density 0.017%

    No Known Activations