© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20967
    Prev
    Next
    INDEX
    Explanations

    terms related to media, entertainment, and notable names

    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
    0:0.05
    1:0.03
    2:0.07
    3:0.06
    4:0.20
    5:0.21
    6:0.03
    7:0.05
    8:0.02
    9:0.11
    10:0.05
    11:0.06
    Negative Logits
     bursting
    -2.50
    ":"","
    -2.46
     overnight
    -2.44
     answered
    -2.40
    ….
    -2.38
    .,"
    -2.38
     […]
    -2.29
    ),"
    -2.26
     altogether
    -2.24
     suddenly
    -2.24
    POSITIVE LOGITS
     Refer
    2.62
     Below
    2.54
     Also
    2.48
    tera
    2.46
     Deter
    2.42
    .)
    2.42
     Examples
    2.40
    pedia
    2.38
    ophon
    2.32
     ).
    2.30
    Activations Density 0.002%

    No Known Activations