© 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. 20677
    Prev
    Next
    INDEX
    Explanations

    references to video games and gaming concepts

    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
    1:0.08
    2:0.08
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.08
    8:0.02
    9:0.04
    10:0.38
    11:0.06
    Negative Logits
     Drag
    -3.45
     Du
    -3.34
     Ded
    -3.29
     Mo
    -3.19
     Cre
    -3.16
     Lod
    -3.16
     Revel
    -3.04
     Sc
    -3.03
    Du
    -3.02
     Se
    -3.01
    POSITIVE LOGITS
     ch
    4.82
     ber
    4.53
     gl
    4.31
     j
    4.28
     l
    4.18
     sh
    4.12
     d
    4.07
     dh
    4.04
     mah
    4.02
     y
    4.01
    Activations Density 0.195%

    No Known Activations