© 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. 12083
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant discussions or features within a certain context

    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
    0:0.08
    1:0.03
    2:0.13
    3:0.22
    4:0.03
    5:0.03
    6:0.02
    7:0.05
    8:0.03
    9:0.01
    10:0.31
    11:0.02
    Negative Logits
    $$$$
    -2.86
    itory
    -2.32
    incarn
    -2.31
    contact
    -2.05
     Tsukuyomi
    -2.01
     *.
    -1.99
     initiation
    -1.98
     arrang
    -1.98
    ascript
    -1.94
    /,
    -1.94
    POSITIVE LOGITS
     noticeably
    2.88
     consistently
    2.68
     misconception
    2.67
     improves
    2.60
     noticed
    2.59
     appreciated
    2.58
     sorely
    2.58
     greatly
    2.56
     weaknesses
    2.53
     flaws
    2.46
    Activations Density 0.142%

    No Known Activations