© 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. 9-ATT-KK
    11. 17623
    Prev
    Next
    INDEX
    Explanations

    concepts related to body image and perceptions of physical attractiveness

    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
    0:0.07
    1:0.02
    2:0.12
    3:0.24
    4:0.03
    5:0.14
    6:0.02
    7:0.08
    8:0.05
    9:0.02
    10:0.13
    11:0.03
    Negative Logits
    clair
    -2.00
    ulous
    -1.96
    raltar
    -1.91
    nil
    -1.88
     unanimous
    -1.86
    ixty
    -1.84
     Anon
    -1.84
    nothing
    -1.82
    76561
    -1.79
    thouse
    -1.78
    POSITIVE LOGITS
     therapies
    3.39
     biomark
    3.33
     therape
    3.25
     treatments
    3.00
     therapeutic
    2.80
     diagn
    2.75
     cures
    2.75
     biomedical
    2.72
     evolutionary
    2.72
     diagnostic
    2.71
    Activations Density 0.192%

    No Known Activations