© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-ATT-KK
    11. 10980
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and mentions of specific companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.02
    2:0.04
    3:0.09
    4:0.03
    5:0.06
    6:0.02
    7:0.11
    8:0.07
    9:0.03
    10:0.19
    11:0.08
    Negative Logits
     manoeuv
    -2.21
     spectators
    -2.19
     ply
    -2.18
    cised
    -2.14
    DCS
    -2.12
     PsyNet
    -2.06
    partial
    -2.06
     Ng
    -2.03
     Psal
    -1.99
     YPG
    -1.98
    POSITIVE LOGITS
     Archives
    2.40
    sonian
    2.31
    Store
    2.21
     Haku
    2.19
    Cooldown
    2.18
     PRODUCT
    2.14
     store
    2.13
    store
    2.11
    Publisher
    2.11
    enegger
    2.05
    Activations Density 0.000%

    No Known Activations