© 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. 10-ATT-KK
    11. 12270
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate existence or state, particularly focusing on verbs of being and their usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.04
    3:0.04
    4:0.05
    5:0.10
    6:0.03
    7:0.06
    8:0.03
    9:0.47
    10:0.02
    11:0.05
    Negative Logits
    姫
    -2.34
    PDATE
    -2.23
    GROUP
    -2.13
    Enlarge
    -2.02
    RANT
    -2.02
    orest
    -2.01
    �
    -1.99
    lished
    -1.98
     [&
    -1.97
    闘
    -1.96
    POSITIVE LOGITS
     is
    2.94
     revolves
    2.84
     was
    2.73
     happens
    2.70
    was
    2.66
     involves
    2.57
     consists
    2.55
     occurs
    2.54
     arises
    2.53
     relates
    2.50
    Activations Density 0.209%

    No Known Activations