© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a long duration of existence or ongoing action

    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
    1:0.02
    2:0.05
    3:0.16
    4:0.01
    5:0.03
    6:0.02
    7:0.08
    8:0.02
    9:0.02
    10:0.48
    11:0.02
    Negative Logits
     later
    -2.26
    oes
    -2.16
     =>
    -2.07
     Conclusion
    -2.07
    nesday
    -1.99
    ####
    -1.99
     Moments
    -1.98
    20439
    -1.94
     Picks
    -1.94
     seconds
    -1.92
    POSITIVE LOGITS
     sheltered
    2.34
     diligently
    2.32
     resisted
    2.27
     endured
    2.27
     tirelessly
    2.24
     resided
    2.21
    pired
    2.21
     hid
    2.15
     stagn
    2.13
     begged
    2.09
    Activations Density 0.060%

    No Known Activations