© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    phrases related to action or significant events and their repercussions

    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
    0:0.06
    1:0.02
    2:0.09
    3:0.19
    4:0.35
    5:0.05
    6:0.02
    7:0.03
    8:0.02
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
    ),"
    -2.47
    .")
    -2.44
     ",
    -2.43
    chard
    -2.42
     "(
    -2.35
    ?",
    -2.33
     "...
    -2.32
    querade
    -2.22
    )",
    -2.21
    ?".
    -2.21
    POSITIVE LOGITS
    ‐
    3.85
    »
    3.83
    **
    3.48
    ♦
    3.33
     �
    3.32
     ­
    3.28
    ————————————————
    3.19
    •
    3.17
     »
    3.15
     •
    3.12
    Activations Density 0.561%

    No Known Activations