© 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. 5-ATT-KK
    11. 44024
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal problems and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.06
    1:0.02
    2:0.04
    3:0.10
    4:0.04
    5:0.13
    6:0.02
    7:0.03
    8:0.07
    9:0.21
    10:0.17
    11:0.07
    Negative Logits
    assad
    -1.14
    inav
    -1.00
    trak
    -0.97
    uania
    -0.95
    luaj
    -0.94
    yip
    -0.88
    idated
    -0.86
     Tus
    -0.85
    orest
    -0.85
    BuyableInstoreAndOnline
    -0.84
    POSITIVE LOGITS
     spoiler
    1.22
     paraph
    1.04
     Spoiler
    1.02
     spoilers
    1.00
     commenter
    0.99
     Gawker
    0.96
     commenters
    0.96
    oiler
    0.95
     Hume
    0.94
     rebutt
    0.91
    Activations Density 3.560%

    No Known Activations