© 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. 21836
    Prev
    Next
    INDEX
    Explanations

    elements related to community engagement and support for local projects

    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
    0:0.17
    1:0.03
    2:0.11
    3:0.15
    4:0.04
    5:0.01
    6:0.11
    7:0.15
    8:0.01
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
     Buc
    -2.91
    wagen
    -2.85
     Patel
    -2.80
    Euro
    -2.71
     Tart
    -2.70
     Polish
    -2.67
     Krug
    -2.66
     Yen
    -2.65
    aido
    -2.56
    veland
    -2.54
    POSITIVE LOGITS
     ABC
    7.02
    ABC
    6.48
     CBS
    4.20
    abc
    4.13
    CBS
    3.83
     NBC
    3.79
     Abbott
    3.64
     Turnbull
    3.38
    NBC
    3.32
     sitcom
    3.24
    Activations Density 0.027%

    No Known Activations