© 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. 13031
    Prev
    Next
    INDEX
    Explanations

    consistent branding and references to official websites or companies

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.04
    4:0.08
    5:0.08
    6:0.04
    7:0.05
    8:0.02
    9:0.12
    10:0.03
    11:0.37
    Negative Logits
    withstanding
    -2.39
    raised
    -2.26
    ��
    -2.17
    phony
    -2.08
    etically
    -2.06
     unheard
    -2.06
    zees
    -2.01
     leaps
    -2.00
     Tradable
    -1.99
     reverber
    -1.97
    POSITIVE LOGITS
     webpage
    4.43
     homepage
    4.25
     page
    4.19
     website
    4.18
     pages
    3.88
     FAQ
    3.74
     wiki
    3.69
    pedia
    3.57
    ipedia
    3.50
     listings
    3.48
    Activations Density 0.203%

    No Known Activations