© 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. 10749
    Prev
    Next
    INDEX
    Explanations

    references to individual identity and business ventures

    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
    1:0.03
    2:0.08
    3:0.05
    4:0.06
    5:0.05
    6:0.14
    7:0.05
    8:0.17
    9:0.13
    10:0.03
    11:0.05
    Negative Logits
     Valhalla
    -4.04
    uliffe
    -3.90
     Malta
    -3.90
     Dracula
    -3.81
     Geral
    -3.74
     Bened
    -3.67
    ł
    -3.60
    aldi
    -3.54
     Bridgewater
    -3.51
     Lazarus
    -3.47
    POSITIVE LOGITS
     soy
    9.98
     Soy
    8.04
     tofu
    7.32
     Asian
    4.73
     rice
    4.62
     Dai
    4.52
     Yam
    4.39
    Asian
    4.35
    Toy
    4.27
    Seattle
    4.18
    Activations Density 0.003%

    No Known Activations