© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    specific classes and character types in gaming contexts

    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
    1:0.04
    2:0.08
    3:0.03
    4:0.13
    5:0.04
    6:0.08
    7:0.17
    8:0.03
    9:0.05
    10:0.05
    11:0.19
    Negative Logits
     malls
    -2.84
    netflix
    -2.47
     beads
    -2.47
     millenn
    -2.29
     dates
    -2.24
     motel
    -2.24
     tracts
    -2.18
     dating
    -2.17
     socks
    -2.13
     advertisements
    -2.12
    POSITIVE LOGITS
     Investigator
    3.27
     Scientist
    3.16
     Healer
    3.16
     Chaser
    3.12
     Sorceress
    2.98
     Berserker
    2.96
     Werewolf
    2.91
     Assass
    2.86
     Unch
    2.86
     Painter
    2.84
    Activations Density 0.010%

    No Known Activations