© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14085
    Prev
    Next
    INDEX
    Explanations

    mentions of agreements, deals, or contracts involving organizations and their implications

    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
    1:0.02
    2:0.02
    3:0.04
    4:0.09
    5:0.22
    6:0.04
    7:0.04
    8:0.01
    9:0.40
    10:0.01
    11:0.04
    Negative Logits
    eret
    -2.33
     everywhere
    -2.19
    itar
    -2.10
    bsite
    -2.09
    camp
    -2.09
    vas
    -2.08
    umblr
    -2.06
    athy
    -2.06
    earch
    -2.02
    chel
    -2.01
    POSITIVE LOGITS
     expires
    3.10
     scrapped
    2.91
     agreed
    2.84
     expired
    2.78
     deadline
    2.76
     stip
    2.74
     guaranteeing
    2.70
     negotiated
    2.62
     vetoed
    2.61
     Signed
    2.60
    Activations Density 0.262%

    No Known Activations