© 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. 15606
    Prev
    Next
    INDEX
    Explanations

    temporal markers or expressions related to time management and expectations

    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
    0:0.03
    1:0.04
    2:0.06
    3:0.10
    4:0.07
    5:0.04
    6:0.03
    7:0.33
    8:0.02
    9:0.06
    10:0.03
    11:0.15
    Negative Logits
     millennial
    -2.49
     Hansen
    -2.39
    RT
    -2.26
    Hub
    -2.20
     Breakfast
    -2.18
    stadt
    -2.17
     Hour
    -2.09
     1830
    -2.08
    HOU
    -2.04
    JR
    -2.03
    POSITIVE LOGITS
     Annotations
    2.32
    sbm
    2.28
     Monstrous
    2.28
    +=
    2.17
    fters
    2.15
    龍喚士
    2.13
     Leilan
    2.11
    icides
    2.05
     appra
    2.05
    $$$$
    2.03
    Activations Density 0.046%

    No Known Activations