© 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. 23795
    Prev
    Next
    INDEX
    Explanations

    references to historical events or artifacts

    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
    0:0.05
    1:0.01
    2:0.08
    3:0.42
    4:0.02
    5:0.10
    6:0.01
    7:0.07
    8:0.09
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
     Spotlight
    -2.46
     VIDEO
    -2.44
    Focus
    -2.42
     HRC
    -2.32
     Updates
    -2.30
    Inside
    -2.27
    Recommend
    -2.27
     Transparency
    -2.27
    Flash
    -2.26
     Insider
    -2.26
    POSITIVE LOGITS
     Ottoman
    3.12
     kings
    3.09
     slaves
    3.06
     colonists
    2.88
     conqu
    2.88
     princes
    2.84
     colonial
    2.83
     ancestors
    2.79
     Britann
    2.79
     kingdoms
    2.78
    Activations Density 1.772%

    No Known Activations