© 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. 504
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their achievements

    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
    0:0.06
    1:0.03
    2:0.06
    3:0.03
    4:0.05
    5:0.02
    6:0.24
    7:0.06
    8:0.05
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
    wcs
    -3.86
     Saga
    -3.56
     Cambodia
    -3.54
     Bosnia
    -3.48
     dried
    -3.48
     Meadow
    -3.46
     ABE
    -3.44
     condom
    -3.44
    orkshire
    -3.43
    avage
    -3.43
    POSITIVE LOGITS
    Leon
    10.55
     Leon
    8.72
     Leonard
    8.41
    leon
    7.38
     Leonardo
    5.08
    STAR
    4.61
     Anton
    4.39
     Leo
    4.09
     Levine
    4.07
     Levy
    3.87
    Activations Density 0.003%

    No Known Activations