© 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. 19776
    Prev
    Next
    INDEX
    Explanations

    terms related to military and defense structures

    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
    1:0.01
    2:0.04
    3:0.05
    4:0.11
    5:0.26
    6:0.04
    7:0.04
    8:0.01
    9:0.24
    10:0.02
    11:0.09
    Negative Logits
    �
    -2.94
     ✓
    -2.83
     0004
    -2.78
    ":[{"
    -2.76
    rame
    -2.66
    antes
    -2.58
    パ
    -2.49
    )</
    -2.48
    アル
    -2.48
    ilar
    -2.41
    POSITIVE LOGITS
     then
    3.12
     until
    3.04
     except
    2.91
     now
    2.76
     argued
    2.73
     oversaw
    2.71
     contended
    2.67
     meanwhile
    2.64
     previously
    2.61
     ousted
    2.58
    Activations Density 0.039%

    No Known Activations