© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19595
    Prev
    Next
    INDEX
    Explanations

    dates and significant years related to events and milestones

    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
    1:0.02
    2:0.05
    3:0.09
    4:0.02
    5:0.18
    6:0.04
    7:0.07
    8:0.03
    9:0.01
    10:0.32
    11:0.04
    Negative Logits
     autopsy
    -2.15
     Buckingham
    -1.95
     Watergate
    -1.92
     curfew
    -1.81
     McDonnell
    -1.80
     diary
    -1.78
     MacArthur
    -1.70
    DCS
    -1.70
     Bomber
    -1.69
     marathon
    -1.66
    POSITIVE LOGITS
     respectively
    2.10
    .}
    2.00
     thanks
    1.97
     indicating
    1.92
     after
    1.92
     whereas
    1.91
     alongside
    1.86
     whilst
    1.85
     ago
    1.84
     as
    1.83
    Activations Density 0.211%

    No Known Activations