© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 25083
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions or reactions to events

    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
    0:0.22
    1:0.14
    2:0.02
    3:0.03
    4:0.02
    5:0.29
    6:0.04
    7:0.01
    8:0.10
    9:0.04
    10:0.02
    11:0.01
    Negative Logits
     inflation
    -1.76
     Gan
    -1.68
     Moz
    -1.67
     Gork
    -1.66
     obstruct
    -1.65
     Takeru
    -1.64
     monop
    -1.62
     sacrific
    -1.59
     ladder
    -1.54
     Airbnb
    -1.54
    POSITIVE LOGITS
    onne
    2.19
    ople
    2.03
    ukes
    1.96
    inese
    1.89
    iola
    1.86
    augh
    1.85
    rique
    1.84
    thouse
    1.83
    ��
    1.83
    ricanes
    1.82
    Activations Density 0.090%

    No Known Activations