© 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. 7779
    Prev
    Next
    INDEX
    Explanations

    keywords related to priority or significance in references to legislation or issues

    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
    0:0.10
    1:0.04
    2:0.07
    3:0.05
    4:0.06
    5:0.05
    6:0.21
    7:0.04
    8:0.04
    9:0.20
    10:0.04
    11:0.05
    Negative Logits
     裏�
    -4.27
     slideshow
    -3.63
     Socialism
    -3.58
    vic
    -3.57
    VA
    -3.48
    Sanders
    -3.42
     SA
    -3.38
    ISO
    -3.37
    atican
    -3.35
    lv
    -3.33
    POSITIVE LOGITS
     Ear
    9.21
    Ear
    9.07
     ear
    8.73
     ears
    6.01
     EAR
    5.64
    ear
    5.21
    EAR
    4.98
     headphones
    4.62
     headphone
    4.58
    lear
    4.36
    Activations Density 0.003%

    No Known Activations