© 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. 35472
    Prev
    Next
    INDEX
    Explanations

    expressions of social criticism and behavior related to aggression toward differing viewpoints

    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
    0:0.03
    1:0.01
    2:0.16
    3:0.12
    4:0.10
    5:0.04
    6:0.01
    7:0.06
    8:0.11
    9:0.07
    10:0.12
    11:0.11
    Negative Logits
    DragonMagazine
    -1.25
     Printed
    -1.15
    staking
    -1.14
     Guinness
    -1.11
     Osborne
    -1.08
     McCartney
    -1.07
     Canary
    -1.04
     Pair
    -1.03
     upgr
    -1.02
     Billboard
    -1.01
    POSITIVE LOGITS
    ��
    1.57
     etc
    1.48
     oppress
    1.48
     unworthy
    1.48
     unjust
    1.42
     detriment
    1.36
     rapists
    1.32
     harms
    1.30
    る
    1.29
     injust
    1.28
    Activations Density 1.107%

    No Known Activations