© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 18514
    Prev
    Next
    INDEX
    Explanations

    phrases related to control, suffering, and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.11
    3:0.05
    4:0.04
    5:0.04
    6:0.25
    7:0.04
    8:0.03
    9:0.23
    10:0.03
    11:0.02
    Negative Logits
     Schro
    -3.81
     Aer
    -3.79
     Kenn
    -3.73
    aceous
    -3.72
     Roz
    -3.57
     Towns
    -3.55
    OAD
    -3.54
    utm
    -3.46
    KT
    -3.43
    VO
    -3.43
    POSITIVE LOGITS
    suff
    6.45
     suffering
    6.22
     suffer
    5.63
     Suff
    5.20
     suffers
    5.17
     suffered
    5.01
    uffer
    4.45
    usterity
    3.92
     suff
    3.84
     Nep
    3.75
    Activations Density 0.001%

    No Known Activations