© 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. 20838
    Prev
    Next
    INDEX
    Explanations

    references to punk culture and community representation

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.26
    7:0.04
    8:0.07
    9:0.18
    10:0.04
    11:0.04
    Negative Logits
     Gleaming
    -3.85
     Invention
    -3.78
     Hig
    -3.60
     Faul
    -3.59
    ||||
    -3.57
     Moroc
    -3.39
     Hugo
    -3.39
     Fry
    -3.38
     Alvin
    -3.37
    hoe
    -3.32
    POSITIVE LOGITS
     CM
    9.35
    CM
    9.15
    cm
    6.66
     cm
    6.55
     Cyan
    5.13
    cms
    4.50
    tm
    4.19
    bm
    4.13
    Clock
    4.00
     CAM
    3.87
    Activations Density 0.001%

    No Known Activations