© 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. 19797
    Prev
    Next
    INDEX
    Explanations

    expressions and symbols related to emotions or excitement

    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
    0:0.18
    1:0.20
    2:0.03
    3:0.03
    4:0.02
    5:0.21
    6:0.08
    7:0.01
    8:0.04
    9:0.07
    10:0.07
    11:0.02
    Negative Logits
    Requirements
    -1.80
     humid
    -1.71
     satur
    -1.64
     ABS
    -1.63
     IPM
    -1.58
    BUS
    -1.58
     muted
    -1.57
     TAG
    -1.57
     HUM
    -1.55
    Marsh
    -1.53
    POSITIVE LOGITS
    ��
    2.40
    vre
    2.35
    alez
    2.34
    iola
    2.31
    olla
    2.24
    ouf
    2.21
    uca
    2.17
    enegger
    2.15
    uin
    2.14
    ople
    2.11
    Activations Density 0.029%

    No Known Activations