© 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. 16532
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or strong assertions in the text

    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
    0:0.07
    1:0.05
    2:0.06
    3:0.06
    4:0.03
    5:0.04
    6:0.21
    7:0.04
    8:0.05
    9:0.28
    10:0.03
    11:0.03
    Negative Logits
    ��
    -3.92
     Regist
    -3.69
    soType
    -3.54
    ococ
    -3.45
     NCT
    -3.44
    ��
    -3.42
     Ober
    -3.37
     Zimmer
    -3.34
     Geral
    -3.25
     Marshal
    -3.23
    POSITIVE LOGITS
     stick
    8.12
     Stick
    7.68
     sticks
    7.47
    stick
    6.74
    sticks
    5.67
     sticking
    5.36
     sticky
    5.13
     stuck
    5.03
     cling
    3.95
    deen
    3.92
    Activations Density 0.008%

    No Known Activations