© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 23415
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement actions and community incidents

    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
    0:0.06
    1:0.01
    2:0.07
    3:0.04
    4:0.04
    5:0.05
    6:0.17
    7:0.03
    8:0.21
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    č
    -4.30
     Philipp
    -4.05
     Serbia
    -3.98
     sv
    -3.90
     Serbian
    -3.76
     Slovenia
    -3.72
     CMS
    -3.68
     MEP
    -3.56
     Sloven
    -3.54
     Dracula
    -3.52
    POSITIVE LOGITS
     Oakland
    10.81
    Oak
    10.63
     Raiders
    6.65
     BART
    6.21
    ameda
    5.94
     Oak
    5.76
     Berkeley
    5.71
    Raid
    5.59
    Detroit
    5.55
     Raider
    5.40
    Activations Density 0.013%

    No Known Activations