© 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. 10-ATT-KK
    11. 14799
    Prev
    Next
    INDEX
    Explanations

    mentions of notable acting roles and television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.04
    2:0.08
    3:0.12
    4:0.15
    5:0.06
    6:0.04
    7:0.10
    8:0.03
    9:0.09
    10:0.04
    11:0.11
    Negative Logits
    inventoryQuantity
    -3.16
     ✔
    -3.13
    ··
    -3.11
    �
    -2.85
    ️
    -2.82
    �
    -2.80
     �
    -2.79
     upgr
    -2.78
    ebin
    -2.77
     �
    -2.70
    POSITIVE LOGITS
     1966
    3.78
     1969
    3.67
    ".[
    3.61
     1975
    3.51
     1974
    3.42
     1955
    3.40
     1976
    3.40
     1978
    3.40
     1971
    3.38
     1968
    3.37
    Activations Density 0.222%

    No Known Activations