© 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. 35916
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or significant emotional expressions

    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
    0:0.04
    1:0.16
    2:0.02
    3:0.07
    4:0.05
    5:0.20
    6:0.08
    7:0.01
    8:0.13
    9:0.09
    10:0.06
    11:0.03
    Negative Logits
     Manit
    -1.44
     experien
    -1.44
     multic
    -1.39
    assetsadobe
    -1.34
     carriage
    -1.33
     centrally
    -1.32
    imil
    -1.27
     autom
    -1.26
     Soldier
    -1.26
     monop
    -1.26
    POSITIVE LOGITS
    yden
    1.73
    �
    1.58
    endif
    1.51
    iola
    1.49
    �
    1.48
    edi
    1.48
    -|
    1.46
    Depth
    1.42
    �
    1.40
    ��
    1.40
    Activations Density 0.044%

    No Known Activations