© 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. 268
    Prev
    Next
    INDEX
    Explanations

    instructions and steps for navigating user interfaces

    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
    0:0.11
    1:0.03
    2:0.08
    3:0.18
    4:0.04
    5:0.25
    6:0.02
    7:0.07
    8:0.04
    9:0.03
    10:0.05
    11:0.03
    Negative Logits
     mockery
    -1.71
     snipers
    -1.58
     hindsight
    -1.55
    DoS
    -1.55
     clerks
    -1.52
     confusion
    -1.51
     pedestrians
    -1.50
     fools
    -1.49
     motorists
    -1.48
     bystanders
    -1.48
    POSITIVE LOGITS
     Selected
    2.42
    ategories
    1.86
     Categories
    1.81
     Schedule
    1.81
     Contents
    1.78
    ibliography
    1.72
    ................................................................
    1.72
     Sources
    1.71
    tab
    1.66
     selected
    1.65
    Activations Density 0.546%

    No Known Activations