© 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. 576
    Prev
    Next
    INDEX
    Explanations

    specific character names or identifiers within narratives

    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
    0:0.05
    1:0.03
    2:0.03
    3:0.06
    4:0.03
    5:0.03
    6:0.11
    7:0.02
    8:0.05
    9:0.47
    10:0.04
    11:0.02
    Negative Logits
     McD
    -4.10
     Feldman
    -4.06
     McKay
    -3.95
     McGregor
    -3.88
     McN
    -3.72
     Cohn
    -3.68
    KEN
    -3.65
     Flan
    -3.60
     McA
    -3.54
     Fa
    -3.50
    POSITIVE LOGITS
    us
    5.85
    ius
    5.46
    asus
    5.45
    rus
    5.14
    lus
    5.07
    US
    4.81
    xus
    4.76
    uses
    4.70
    itus
    4.62
    anus
    4.57
    Activations Density 0.020%

    No Known Activations