© 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. 9-ATT-KK
    11. 20286
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.07
    3:0.04
    4:0.05
    5:0.03
    6:0.15
    7:0.05
    8:0.05
    9:0.38
    10:0.02
    11:0.03
    Negative Logits
    arine
    -4.21
    arte
    -4.02
    arde
    -3.93
    ARC
    -3.67
     Xen
    -3.54
     Ethernet
    -3.48
    ��
    -3.46
     Takeru
    -3.33
    ingen
    -3.30
    aldo
    -3.30
    POSITIVE LOGITS
     Josh
    9.32
    Josh
    9.04
     Joshua
    6.80
    Joshua
    6.56
    OSH
    5.26
     Boyle
    4.05
    osh
    4.02
     Seth
    3.75
     Craig
    3.67
     Shah
    3.63
    Activations Density 0.010%

    No Known Activations