© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9348
    Prev
    Next
    INDEX
    Explanations

    references to subscription and engagement with content

    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
    0:0.14
    1:0.05
    2:0.04
    3:0.08
    4:0.09
    5:0.07
    6:0.12
    7:0.08
    8:0.04
    9:0.06
    10:0.14
    11:0.04
    Negative Logits
     Qt
    -3.61
     Polaris
    -3.23
     Kazakh
    -3.21
     Pence
    -3.20
    Tai
    -3.01
     fox
    -2.96
     Murdoch
    -2.95
     TT
    -2.93
     Summon
    -2.83
     Vega
    -2.81
    POSITIVE LOGITS
    liga
    3.57
    amer
    2.55
     Mortgage
    2.55
    ategory
    2.54
     Glad
    2.54
     Jer
    2.54
     Cla
    2.53
    és
    2.51
     Beaver
    2.50
     Leather
    2.50
    Activations Density 0.002%

    No Known Activations