© 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. 7403
    Prev
    Next
    INDEX
    Explanations

    sentiments related to traditional role-playing game mechanics and their perceived misunderstandings within the gaming community

    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
    0:0.15
    1:0.04
    2:0.12
    3:0.07
    4:0.06
    5:0.01
    6:0.13
    7:0.10
    8:0.03
    9:0.03
    10:0.13
    11:0.07
    Negative Logits
     Bronx
    -2.86
     borough
    -2.80
     Rockefeller
    -2.78
     McKin
    -2.78
     Cort
    -2.75
     Jamaica
    -2.75
     Barclays
    -2.72
    ewitness
    -2.69
    ockey
    -2.66
    cert
    -2.66
    POSITIVE LOGITS
     RPG
    7.13
    RPG
    6.64
     RPGs
    6.42
     DRAG
    3.88
     dungeon
    3.62
     Mages
    3.50
     Rowling
    3.49
     Dungeon
    3.48
     DPS
    3.46
     DM
    3.41
    Activations Density 0.001%

    No Known Activations