© 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. 5-ATT-KK
    11. 3927
    Prev
    Next
    INDEX
    Explanations

    references to targeting specific groups or categories, particularly in contexts related to discrimination or advertising

    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
    0:0.01
    1:0.01
    2:0.05
    3:0.10
    4:0.31
    5:0.02
    6:0.03
    7:0.20
    8:0.03
    9:0.03
    10:0.06
    11:0.08
    Negative Logits
    ACP
    -1.85
    VERTISEMENT
    -1.56
     Congratulations
    -1.56
     Conclusion
    -1.48
     confir
    -1.48
    CHO
    -1.38
    arthed
    -1.37
    iesta
    -1.36
    haps
    -1.36
    Recomm
    -1.34
    POSITIVE LOGITS
     targets
    1.91
     specifically
    1.69
     sectors
    1.62
    netflix
    1.62
     areas
    1.61
     intersections
    1.59
     URLs
    1.52
     fronts
    1.51
     keywords
    1.51
     constituencies
    1.49
    Activations Density 0.017%

    No Known Activations