© 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. 15757
    Prev
    Next
    INDEX
    Explanations

    phrases related to discomfort and the need for comfort

    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
    0:0.12
    1:0.18
    2:0.04
    3:0.04
    4:0.07
    5:0.03
    6:0.08
    7:0.15
    8:0.02
    9:0.03
    10:0.08
    11:0.10
    Negative Logits
     Binary
    -2.54
    mson
    -2.41
     Gemini
    -2.38
    iolet
    -2.30
     Flowers
    -2.29
     Dum
    -2.29
     Bou
    -2.27
     Carey
    -2.26
    EStream
    -2.23
     Vand
    -2.23
    POSITIVE LOGITS
     Comfort
    4.07
     comfort
    3.93
     comfortable
    3.64
    comfort
    3.60
    fortable
    2.99
     snug
    2.60
     uncomfortable
    2.60
    forts
    2.59
     ease
    2.45
     comforting
    2.41
    Activations Density 0.004%

    No Known Activations