© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    references to legal and political processes or entities

    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
    0:0.04
    1:0.02
    2:0.11
    3:0.32
    4:0.14
    5:0.11
    6:0.03
    7:0.05
    8:0.04
    9:0.05
    10:0.02
    11:0.03
    Negative Logits
    …
    -4.46
    ".[
    -4.35
    "…
    -4.32
    !".
    -4.30
    …"
    -4.21
    ?".
    -3.73
     [/
    -3.69
    ..
    -3.60
    [/
    -3.51
     whilst
    -3.48
    POSITIVE LOGITS
    Newsletter
    6.27
     ''
    4.37
    ,''
    4.15
     )]
    3.02
     Latter
    2.99
    .)
    2.98
    20439
    2.90
    .''
    2.83
     afterward
    2.80
     Rodham
    2.76
    Activations Density 0.168%

    No Known Activations