© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    key terms related to governance and regulatory issues

    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
    0:0.02
    1:0.03
    2:0.03
    3:0.04
    4:0.08
    5:0.52
    6:0.02
    7:0.03
    8:0.02
    9:0.09
    10:0.04
    11:0.03
    Negative Logits
    tained
    -3.24
    ahime
    -3.15
    had
    -3.05
    Had
    -2.90
    este
    -2.85
     tho
    -2.85
     Had
    -2.63
    ciating
    -2.63
    anka
    -2.59
     despite
    -2.57
    POSITIVE LOGITS
     becomes
    5.56
     will
    5.14
     ceases
    5.13
    'll
    4.68
     wont
    4.58
     MUST
    4.57
     WILL
    4.54
     disappears
    4.41
     loses
    4.29
    will
    4.27
    Activations Density 0.619%

    No Known Activations