© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technology and media products

    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
    0:0.04
    1:0.35
    2:0.06
    3:0.06
    4:0.05
    5:0.04
    6:0.07
    7:0.03
    8:0.04
    9:0.10
    10:0.06
    11:0.05
    Negative Logits
    yet
    -3.08
    beit
    -3.05
     Yet
    -2.79
    merce
    -2.73
    iates
    -2.65
    Yet
    -2.57
    pite
    -2.56
    ockets
    -2.45
     sqor
    -2.36
    ason
    -2.36
    POSITIVE LOGITS
     called
    4.51
     Called
    4.11
    called
    4.01
     Skydragon
    3.86
     named
    3.71
     termed
    3.55
     nicknamed
    3.18
    named
    3.13
     dubbed
    3.09
     referred
    2.86
    Activations Density 0.002%

    No Known Activations