© 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. 16693
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional responses and social reactions

    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
    0:0.03
    1:0.04
    2:0.03
    3:0.03
    4:0.09
    5:0.05
    6:0.04
    7:0.08
    8:0.02
    9:0.12
    10:0.03
    11:0.38
    Negative Logits
    Myth
    -2.31
     Accounting
    -2.30
    tab
    -2.19
     recorder
    -2.14
     plot
    -2.07
     planner
    -2.07
     Contracts
    -2.06
     schedule
    -2.04
     tab
    -2.02
    Missing
    -2.01
    POSITIVE LOGITS
     reactions
    4.04
     reaction
    4.02
     responses
    3.65
     replies
    3.62
     response
    3.50
     backlash
    3.44
     comments
    3.21
     vitri
    3.17
    Response
    3.13
     outcry
    3.07
    Activations Density 0.166%

    No Known Activations