© 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. 10-ATT-KK
    11. 9907
    Prev
    Next
    INDEX
    Explanations

    references to police and legal actions related to protests and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.07
    2:0.07
    3:0.08
    4:0.04
    5:0.01
    6:0.09
    7:0.07
    8:0.04
    9:0.03
    10:0.23
    11:0.04
    Negative Logits
     mog
    -3.93
    zona
    -3.85
    ILA
    -3.69
     Pand
    -3.60
     pes
    -3.43
     Philippine
    -3.37
     Nicaragua
    -3.33
    Ari
    -3.29
     Sloven
    -3.29
     Mex
    -3.24
    POSITIVE LOGITS
     Durham
    9.68
    Dur
    6.48
     Raleigh
    5.07
     Burr
    4.73
     Duke
    4.70
     Charlotte
    4.32
     Chapel
    4.17
     Cary
    4.14
     Wake
    4.14
     Dun
    4.02
    Activations Density 0.006%

    No Known Activations