© 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. 16790
    Prev
    Next
    INDEX
    Explanations

    references to controversial or sensitive topics

    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
    1:0.09
    2:0.08
    3:0.03
    4:0.03
    5:0.03
    6:0.26
    7:0.08
    8:0.02
    9:0.04
    10:0.11
    11:0.02
    Negative Logits
    ��
    -3.40
    vell
    -2.86
     Mata
    -2.84
    skirts
    -2.70
    dos
    -2.69
    anes
    -2.66
    flush
    -2.65
     Sultan
    -2.60
    uld
    -2.54
    aca
    -2.52
    POSITIVE LOGITS
    Jeremy
    7.45
     Jeremy
    7.35
     Corbyn
    4.05
     Clarkson
    3.16
     Owen
    3.06
     Jimmy
    2.96
     Jericho
    2.95
     Blair
    2.93
     endorsements
    2.82
    Jimmy
    2.77
    Activations Density 0.008%

    No Known Activations