© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14432
    Prev
    Next
    INDEX
    Explanations

    references to arousal and its physiological measurements

    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
    0:0.15
    1:0.08
    2:0.06
    3:0.08
    4:0.08
    5:0.02
    6:0.06
    7:0.12
    8:0.03
    9:0.04
    10:0.12
    11:0.11
    Negative Logits
     Miche
    -3.62
    atown
    -2.87
     Badge
    -2.80
     boarded
    -2.72
     Tata
    -2.71
     Undead
    -2.67
     ★
    -2.66
    ilts
    -2.57
    oyal
    -2.51
    rolet
    -2.47
    POSITIVE LOGITS
     orgasm
    6.39
     ejac
    5.47
     clitor
    5.03
     org
    4.92
     vaginal
    4.14
     masturbation
    3.91
     pelvic
    3.70
     climax
    3.69
     masturb
    3.50
     cum
    3.40
    Activations Density 0.002%

    No Known Activations