© 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. 5-ATT-KK
    11. 17879
    Prev
    Next
    INDEX
    Explanations

    key terms related to rules and instructions in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.36
    2:0.04
    3:0.04
    4:0.03
    5:0.13
    6:0.04
    7:0.04
    8:0.04
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    Tweet
    -2.27
    Sym
    -2.24
     Synd
    -2.21
    Gam
    -2.01
     Spir
    -1.98
     Reson
    -1.83
     Ste
    -1.78
     Sym
    -1.77
    Ped
    -1.76
     Ped
    -1.76
    POSITIVE LOGITS
     ONLY
    2.21
    only
    2.20
    ateurs
    2.10
     exclusively
    2.02
     contrace
    2.02
     ordinarily
    2.01
     only
    1.93
     predominantly
    1.83
    inois
    1.82
    uana
    1.82
    Activations Density 0.003%

    No Known Activations