© 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. 21874
    Prev
    Next
    INDEX
    Explanations

    references to nudity and societal attitudes towards it

    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
    0:0.20
    1:0.10
    2:0.05
    3:0.06
    4:0.08
    5:0.03
    6:0.05
    7:0.06
    8:0.03
    9:0.06
    10:0.16
    11:0.07
    Negative Logits
     HC
    -3.41
     Mayweather
    -3.33
    McC
    -3.30
     Prescott
    -3.25
     Herrera
    -3.15
     Herz
    -3.15
    ibles
    -3.13
     Dynamo
    -3.10
     Cole
    -3.08
    Cole
    -2.97
    POSITIVE LOGITS
     nud
    8.54
     nude
    4.76
     nudity
    4.59
     Tsuk
    4.33
    atur
    3.56
    pn
    3.55
     Nad
    3.50
     Mermaid
    3.46
     mammal
    3.42
     Naked
    3.42
    Activations Density 0.001%

    No Known Activations